23rd ACM International Conference on Multimedia
Conference Program
26–30 October 2015, Brisbane, Australia
Welcome to the ACM Multimedia Conference for 2015, the premier conference for multimedia
experts and practitioners across academia and industry. Since the founding of ACM SIGMM in
1993, ACM Multimedia has been the worldwide premier conference and a key world event to
display scientific achievements and innovative industrial products in the multimedia field.
For the first time in its history, ACM Multimedia 2015 will be held in the Spring season in Brisbane,
the capital city of the “Sunshine State” in Australia, at the Brisbane Convention and Exhibition
Centre from 26 – 30 October 2015.
At ACM Multimedia 2015, we will present an extensive program consisting of technical sessions
covering all aspects of the multimedia field via oral, video and poster presentations, tutorials,
panels, exhibits, demonstrations, workshops, doctoral symposium, multimedia grand challenge,
brave new ideas on shaping the research landscape, open source software competition, and
also an interactive arts program stimulating artists and computer scientists to meet and discover
together the frontiers of artistic communication.
Sponsors
Association for Computing Machinery (ACM)
Special Interest Group on Multimedia (SIGMM)
Gold Level
Baidu
FX Palo Alto Laboratory (FXPAL)
National Science Foundation (NSF)
University of Electronic Science and Technology of China (UESTC)
The University of Queensland, Australia
Silver Level
Alibaba Group
City of Brisbane
Google
Queensland University of Technology
The University of Sydney
Bronze Level
Facebook
Huawei
HTC
IBM Research
Microsoft Research
Yahoo! Labs
Contents
General Chairs’ Welcome......................................................................................................... 2
Message from Technical Program Chairs.................................................................................. 3
Message from SIGMM Chair..................................................................................................... 6
ACM SIGMM/TOMM 2015 Award Announcements.................................................................. 8
Conference Venue.................................................................................................................... 9
Program at a Glance............................................................................................................... 10
Tutorials and Workshops – Monday 26 October............................................................... 10
Conference Day 1 – Tuesday 27 October......................................................................... 12
Conference Day 2 – Wednesday 28 October.................................................................... 14
Conference Day 3 – Thursday 29 October........................................................................ 16
Workshops – Friday 30 October....................................................................................... 18
Keynotes................................................................................................................................ 20
Art Exhibit............................................................................................................................... 24
Monday 26 October – Tutorials............................................................................................ 25
Half Day Tutorials (1, 2, 3, 6, 7, 8) .................................................................................... 25
Full Day Tutorials (4, 5) ..................................................................................................... 31
Monday 26 October – Workshops....................................................................................... 34
Tuesday 27 October – Conference Day 1............................................................................. 37
Wednesday 28 October – Conference Day 2....................................................................... 51
Thursday 29 October – Conference Day 3........................................................................... 66
Friday 30 October – Workshops........................................................................................... 77
Social Program....................................................................................................................... 87
Conference Organization and Committees.............................................................................. 88
Registration and Information Desk........................................................................................ 101
Transport.............................................................................................................................. 102
ACM Multimedia 2015 Conference
1
General Chairs’ Welcome
It is our great pleasure to welcome you to the 2015 ACM MULTIMEDIA Conference, the premier
conference for multimedia experts and practitioners from across academia and industry. This year we
are in beautiful Brisbane, Australia, our first time in this wonderful country and we’re delighted to be
here and looking forward to experiencing some of the delights and treasures this great country has to
offer.
This year’s conference is the 23rd in the annual series continues our tradition to bring together a
wide and diverse set of activities including panel sessions, tutorials, a series of workshops, technical
demos, an open source software competition, a doctoral symposium, an interactive art exhibition, a
video program and of course scientific papers and posters including special sessions on brave new
ideas and grand challenges, as well as “regular” topics. What a busy week we are going to have!
One of the great parts of the program that we have lined up for you is the two keynote talks.
On Tuesday October 27th, Judy Kay from the University of Sydney will talk about “Harnessing
Big Personal Data, with scrutable user modeling for privacy and control”, bringing her extensive
background in Human-Computer Interaction to the really topical issue of personal data, and how
to manage and use it for good and practical purposes. On Thursday October 29th, Zhengyou
Zhang from Microsoft Research will talk about “Vision-enhanced Immersive Interaction and Remote
Collaboration with Large Touch Displays” where he will address issues like telepresence and
computer supported cooperative work and how those technologies have, and continue to develop.
We are immensely grateful to the University of Queensland, our hosts and local organizers, for
inviting us here to Brisbane and for organizing such a great event. We also thank our gold sponsors
ACM SIGMM, the University of Queensland, the National Science Foundation, FXPAL, Baidu, and
the University of Electronic Science and Technology China, our silver sponsors Google, Queensland
University of Technology, the Alibaba Group, the University of Sydney and Brisbane Marketing, and
our bronze sponsors Huawei, IBM Research, Microsoft Research, HTC, Facebook and Yahoo! Labs.
Without their support this conference would simply not be what it is today.
Of course putting together MULTIMEDIA 2015 was a team effort and there are large number of
people we should thank including authors, the program committee, area chairs, chairs of a myriad of
other conference-related functions, local organizers and volunteers, We would like to make a special
call out to Roger Zimmerman and Yongdong Zhang our proceedings chairs for the enormous amount
of work they have done in the background to bring all this material together into one volume.
Finally, we hope that you will find the program for Multimedia 2015 interesting and thoughtprovoking and that you use the opportunity to share and exchange ideas with other researchers and
practitioners from around the world.
Welcome to Brisbane.
Xiaofang Zhou
The University of Queensland,
Australia
Alan F. Smeaton
Dublin City University,
Ireland
ACM MULTIMEDIA’15 General Chairs
2
ACM Multimedia 2015 Conference
Qi Tian
The University of Texas at
San Antonio, USA
Message from Technical Program
Chairs
We are pleased to introduce to you the Technical Program for the ACM International Conference
on Multimedia (ACM Multimedia) 2015, for its first appearance in the Southern hemisphere.
While adopting the best practices from previous ACM Multimedia conferences, this year we also
introduced some changes on the research areas, the review process, and the conference program
to reflect and ensure the greatest interests of researchers in our multimedia community.
Fifteen research areas of interest were grouped into four research themes, including a System
Theme (covering Multimedia Telepresence and Virtual/Augmented Reality, Multimedia Systems and
Middleware, Multimedia Transport and Delivery, Mobile Multimedia), an Experience Theme (covering
Multimedia for Collaboration in Education & Distributed Environments, Multimedia HCI and Quality
of Experience, Music, Speech and Audio Processing in Multimedia, Multimedia Authoring and
Enrichment), an Understanding Theme (covering Deep Learning for Multimedia, Multimodal Analysis
and Description, Multimedia and Vision), and an Engagement Theme (covering Multimedia Art,
Entertainment and Culture, Multimedia Search and Recommendation, Social Multimedia, Emotional
and Social Signals In Multimedia). In particular, the area of Multimedia and Vision was introduced
to reach out to the relevant community that mainly deals with processing vision-related multimedia
data.
This year, CMT was used to manage paper submissions and each research theme was set up
as a track in the system. While CMT worked well for most steps in the review process, moving
submissions across tracks was not allowed. In CMT, the Conflict of Interest (CoI) was easily
handled by authors who had to specify the conflicting domains, Area Chairs and reviewers before
they could make submissions.
Each research theme was overseen by one Technical Program Chair. For each area, a team of Area
Chairs (ACs) of one to five members was recruited to handle the paper review process. In total, 37
ACs were appointed. Technical Program Chairs firstly assigned three or four reviewers and one or
two ACs to each full and short submission. ACs then monitored the review process, coordinated
discussions based on feedback, assessed the submissions based on reviews, and provided metarecommendations as the inputs for the Technical Programme Committee (TPC) meeting.
While the general practices for ACs as stated in previous ACM Multimedia conferences were
followed, this year we introduced the pairing relationship between two ACs to look at all borderline
papers. If a submission received an initial borderline recommendation, another AC with relevant
expertise was brought in to provide another examination of the submission before a final decision
was made.
Regarding the paper submission and review process,
•
As in 2014, there was no pre-submission of abstracts. Submissions of full and short papers
were separated from each other, with the short paper submission deadline being one month
later than the deadline for full paper submissions.
ACM Multimedia 2015 Conference
3
•
As in 2014, for full papers, a two-stage review process was applied. Authors were invited to
submit a rebuttal based on the first stage reviews. The reviewers were then asked to consider
the rebuttal, to revise their reviews accordingly, and to enter discussion with other reviewers
aiming to improve review consensus on each paper. The results of the second round reviews
and discussion were then summarized by the ACs into meta-reviews, which included tentative
recommendations, to be discussed and finalized during the TPC meeting. In the second stage
review, authors had the opportunity to talk to the Authors’ Advocate if they felt they had issues
with the reviews.
•
For any submission with a borderline recommendation, an additional AC was paired with the
initially assigned AC to provide a second recommendation, to be further discussed and finalized
during the TPC meeting.
•
Submissions from Technical Program Chairs and ACs were handled personally by nonconflicting Technical Program Chairs.
•
In total, 252 full and 386 short paper submissions were received by their respective deadlines
and entered the regular review process.
•
The table below gives the exact submission numbers across research areas.
Area
Full
Short
Multimedia Telepresence and Virtual/Augmented Reality
12
11
Multimedia Systems and Middleware
16
23
Multimedia Transport and Delivery
11
8
Mobile Multimedia
16
15
Multimedia for Collaboration in Education & Distributed Environments
8
5
16
17
Music, Speech and Audio Processing in Multimedia
7
18
Multimedia Authoring and Enrichment
3
8
Deep Learning for Multimedia
8
34
Multimodal Analysis and Description
26
43
Multimedia and Vision
43
94
Multimedia Art, Entertainment and Culture
16
11
Multimedia Search and Recommendation
40
59
Social Multimedia
18
17
Emotional and Social Signals In Multimedia
12
23
252
386
Multimedia HCI and Quality of Experience
Total
4
ACM Multimedia 2015 Conference
Decisions on full and short paper acceptances were made at the one-day TPC meeting held at
Fudan University on 22 June 2015. All four Technical Program Chairs attended the meeting and
handled their own themes in four different rooms separately. The emphasis of the TPC meeting was
on high-score, borderline, and controversial paper submissions. The discussion was intensive, taking
into account all the available data, including reviews, the authors’ rebuttals, the discussions, the initial
recommendations by the ACs (in the form of a meta review) and the reviews performed by other ACs
during the meeting. Technical Program Chairs and ACs were requested to leave the room when a
conflicting submission was discussed.
After the meeting, the four TPC Chairs met to make final decisions, taking quality and balance of
different tracks into consideration. By end of the day, we accepted 56 full and 117 short papers,
leading to acceptance rates of 22.2% and 30.3% for full and short papers, respectively. Eight high
quality full paper submissions had also been suggested to be accepted as short papers.
In a change from previous years, we also arranged a poster session for orally presented papers,
including full and BNI papers, to be presented as posters to increase interactions among conference
attendees. A number of TOMM papers published in 2014 were also invited to be presented in this
poster session, to promote their research results as reported in TOMM.
The Technical Program Committee has worked really hard to ensure that the technical program
of the conference is of the highest possible quality. Unfortunately, we couldn’t include every single
quality paper into the program. We really appreciate all the efforts and inputs from ACs and reviewers
towards the exciting technical program.
We look forward to seeing you in the season of Spring, in Brisbane, Australia.
Dick Bulterman
FXPal, USA
Heng Tao Shen
The University of
Queensland, Australia
Ketan Mayer-Patel
The University of North
Carolina, USA
Shuicheng Yan
National University of
Singapore
ACM Multimedia 2015 Conference
5
Message from SIGMM Chair
T-Shaped Vision, New Initiative, and Great Tradition
Different from other professional societies, the technical activities in ACM are organized around
SIG, which stands for Special Interest Group. Each SIG is focused on a specific disciplinary area.
In our case, it’s Multimedia, a relatively broad but vaguely defined field covering a wide spectrum of
aspects surrounding multimedia – computing, communications, and applications. However, there
is a unique force that makes our community continue to excel and thrive: it’s the dynamic crossdisciplinary nature of the intellectual pursuit of novel solutions in response to grand challenges facing
the community at various times, starting with streaming and storage of multimedia data in the 90’s, to
rich media interaction (including overcoming the semantic gap in accessing web-scale multimedia),
large-scale media sensing and processing over distributed platforms (including Internet of Things),
collaborative environments incorporating rich sensory data and peta-scale networks, finally to the
emerging cognitive multimedia systems involving affective computing and sociopsychological study.
The outcomes of such dynamic interdisciplinary efforts are both deep and broad, underscoring
an important theme identified in the recent SIGMM retreat held in November 2014. A concrete
recommendation made by 28 volunteer leaders in that retreat was the T-shaped vision for SIGMM
– SIGMM should continue to embrace both depth (the vertical line of T) and breadth (the horizontal
bar of T). We should welcome and encourage research of “X and Multimedia” (X being works
from other individual “narrow” disciplines), while aiming to develop the core foundation of our field,
including but not limited to multimedia integration, experience, representation, devices, contexts, and
distributed computing.
I am delighted to see this upcoming ACM Multimedia Conference demonstrates excellent execution
of the above T-shaped vision. The technical program, including an impressive array of regular and
special activities, fully embodies the balanced spirit. You can find in-depth studies of foundational
topics as well as applications of multimedia solutions in many practical domains.
This year also marks the launching of an important initiative – the inaugural SIGMM Multimedia
Frontiers Workshop, featuring 12 rising star researchers in multimedia. These speakers will share
their achievements and visions through invited talks, followed by open dialogs with senior members
in the community. These rising members are at the height of their career and, together with the senior
colleagues, in perfect positions to shape the future direction of the community. The workshop has
been organized with broad input from the Executive Committee and many other volunteers, but the
list of speakers is by no means complete. We look forward to continuing this new initiative in the
future to benefit from views from other rising members.
A great tradition at ACMMM is celebration of the extraordinary achievements of SIGMM members.
This year we are privileged to recognize the exceptional achievements of the following members:
Dr. Tat-Seng Chua for SIGMM Technical Achievement Award, Dr. Yu-Gang Jiang for SIGMM Rising
6
ACM Multimedia 2015 Conference
Star Award, and Dr. Ting Yao for SIGMM Best Ph.D. Thesis Award. These are the prestigious
honors bestowed upon members for their outstanding contributions. Each recipient will address the
conference audience in plenary presentations to share their exciting accomplishments. We thank the
award committees (chaired by Rainer Lienhart) for their hard work in making the selections from the
nominations.
Finally, we are all profoundly indebted to the organizing team of ACM Multimedia 2015 for their
devoted efforts that make ACMMM15 possible and more importantly sustains the success of
SIGMM. We salute them for their invaluable leadership and contributions!
Shih-Fu Chang,
Columbia University, USA,
ACM SIGMM Chair
ACM Multimedia 2015 Conference
7
ACM SIGMM/TOMM 2015
Award Announcements
The ACM Special Interest Group in Multimedia (SIGMM) and ACM Transactions on Multimedia
Computing, Communications and Applications (TOMM) are pleased to announce the following
awards for 2015 recognizing outstanding achievements and services made in the multimedia
community.
SIGMM Award for Outstanding Technical Contributions to Multimedia Computing,
Communications and Applications
Dr. Tat-Seng Chua (National University of Singapore)
ACM SIGMM Rising Star Award
Dr. Yu-Gang Jiang (Fudan University, China)
SIGMM Outstanding Ph.D. Thesis Award
Dr. Ting Yao (City University of Hong Kong) (Microsoft Research)
TOMM Nicolas D. Georganas Best Paper Award
“A Quality of Experience Model for Haptic Virtual Environments” by Abdelwahab Hamam,
Abdulmotaleb El Saddik, and Jihad Alja‘am, published in TOMM, Vol. 10, Issue 3, 2014
TOMM Best Associate Editor Award
Dr. Pradeep K. Atrey (State University of New York, Albany, USA)
8
ACM Multimedia 2015 Conference
Conference Venue
MM-15 will be held in the Plaza Auditorium and meeting rooms P6 – P11, at the Brisbane
Convention & Exhibition Centre [BCEC]. The best entrance point for the Plaza level is Grey Street.
South Brisbane train station is a short walk to/from BCEC.
Below is a map of the Plaza Auditorium and meeting rooms P6 – P11.
All conference sessions and catering will be held in this area.
ACM Multimedia 2015 Conference
9
Program at a Glance
Tutorials and Workshops – Monday 26 October
Auditorium Foyer
8:00 – 9:00
Auditorium
SIGMM Inaugural
Workshop on
Multimedia Frontiers
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
AVEC – Audio/Visual
Emotion Challenge and
Tutorial 1 –
Workshop
VM Hub: Building
Cloud Service and
Mobile Application
Morning Tea
11:00 – 11:30
11:30 – 12:00
SIGMM Inaugural
Workshop on
Multimedia Frontiers
AVEC – Audio/Visual
Tutorial 1 –
Emotion Challenge and VM Hub: Building
Workshop
Cloud Service and
Mobile Application
SIGMM Inaugural
Workshop on
Multimedia Frontiers
AVEC – Audio/Visual
Tutorial 2 – Interactive
Emotion Challenge and Video Search
Workshop
SIGMM Inaugural
Workshop on
Multimedia Frontiers
AVEC – Audio/Visual
Tutorial 2 – Interactive
Emotion Challenge and Video Search
Workshop
12:00 – 12:30
12:30 – 13:30
P7
Welcome Tea/Coffee
8:30 – 9:00
10:30 – 11:00
P6
BREAK
13:30 – 14:00
14:00 – 14:30
14:30 – 15:00
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
Afternoon Tea
16:30 – 17:00
10
ACM Multimedia 2015 Conference
P8
P9
P10
P11
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
Tutorial 3 – Learning
Knowledge Bases for
Multimedia in 2015
Tutorial 4 – Image
Tag Assignment,
Refinement and
Retrieval
Tutorial 5 –
Emotional and
Social Signals for
Multimedia Research
Tutorial 7 – Humancentric images and
videos analysis
Tutorial 3 – Learning
Knowledge Bases for
Multimedia in 2015
Tutorial 4 – Image
Tag Assignment,
Refinement and
Retrieval
Tutorial 5 –
Emotional and
Social Signals for
Multimedia Research
Tutorial 7 – Humancentric images and
videos analysis
Tutorial 6 – An
Introduction to Arts
and Digital Culture
inside Multimedia
Tutorial 4 – Image
Tag Assignment,
Refinement and
Retrieval
Tutorial 5 –
Emotional and
Social Signals for
Multimedia Research
Tutorial 8 –
User-centric CrossOSN Multimedia
Computing
Tutorial 6 – An
Introduction to Arts
and Digital Culture
inside Multimedia
Tutorial 4 – Image
Tag Assignment,
Refinement and
Retrieval
Tutorial 5 –
Emotional and
Social Signals for
Multimedia Research
Tutorial 8 –
User-centric CrossOSN Multimedia
Computing
10:00 – 10:30
10:30 – 11:00
11:00 – 11:30
11:30 – 12:00
12:00 – 12:30
12:30 – 13:30
13:30 – 14:00
14:00 – 14:30
14:30 – 15:00
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
ACM Multimedia 2015 Conference
11
Program at a Glance (continued)
Conference Day 1 – Tuesday 27 October
Auditorium Foyer
8:30 – 9:00
Auditorium
P6 – P11 Foyer
P6
P7
Welcome Tea/Coffee
9:00 – 9:30
9:30 – 10:00
Industry Booths
Keynote 1
10:00 – 10:30
10:30 – 11:00
Morning Tea
11:00 – 11:30
11:30 – 12:00
Industry Booths
Best Paper
12:00 – 12:30
12:30 – 14:00
Women in
SIGMM Lunch
LUNCH
JMM Meeting
14:00 – 14:30
14:30 – 15:00
Industry Booths
Panel 1
Poster 1 –
Short Papers
Oral 1
Poster 1 –
Short Papers
Oral 2
15:00 – 15:30
15:30 – 16:00
Afternoon Tea
16:00 – 16:30
16:30 – 17:00
17:00 – 17:30
Industry Booths
Open Source
Software Comp
17:30 – 18:00
18:00 – 19:00
19:00 – 20:00
12
ACM Multimedia 2015 Conference
P8
P9
P10
P11
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
10:30 – 11:00
11:00 – 11:30
11:30 – 12:00
Demos/Video 1
12:00 – 12:30
12:30 – 14:00
TOMM Meeting
14:00 – 14:30
14:30 – 15:00
Demos/Video 1
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
Oral 3
Demos/Video 1
17:00 – 17:30
Plaza North Terrace
17:30 – 18:00
18:00 – 19:00
19:00 – 20:00
Art Exhibit
Opening
Art Exhibit
Opening
Welcome Reception
ACM Multimedia 2015 Conference
13
Program at a Glance (continued)
Conference Day 2 – Wednesday 28 October
Auditorium Foyer
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
Industry Booths
10:00 – 10:30
10:30 – 11:00
Auditorium
P6 – P11 Foyer
P6
P7
Welcome Tea/Coffee
SIGMM Awards
and Plenary
Talks
Morning Tea
11:00 – 11:30
11:30 – 12:00
Industry Booths
Grand Challenge
Presentations
12:00 – 12:30
12:30 – 14:00
LUNCH
MM-Mag
Meeting
MMSJ Meeting
Oral 5
Oral 6
14:00 – 14:30
14:30 – 15:00
Industry Booths
Brave New
Ideas
Poster 2 – Short
Papers
Oral 4
Poster 2 – Short
Papers
15:00 – 15:30
15:30 – 16:00
Afternoon Tea
16:00 – 16:30
16:30 – 17:00
Industry Booths
17:00 – 17:30
17:30 – 18:00
18:00 – 21:00
14
ACM Multimedia 2015 Conference
P8
P9
P10
P11
Demos 2
Art Exhibit
Art Exhibit
Demos 2
Art Exhibit
Art Exhibit
Demos 2
Art Exhibit
Art Exhibit
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
10:30 – 11:00
11:00 – 11:30
11:30 – 12:00
12:00 – 12:30
12:30 – 14:00
Doctoral
Symposium
14:00 – 14:30
14:30 – 15:00
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
Oral 7
17:00 – 17:30
17:30 – 18:00
City Hall
18:00 – 21:00
Banquet – City Hall
ACM Multimedia 2015 Conference
15
Program at a Glance (continued)
Conference Day 3 – Thursday 29 October
Auditorium Foyer
8:30 – 9:00
Auditorium
P6 – P11 Foyer
P6
Welcome Tea/Coffee
9:00 – 9:30
9:30 – 10:00
Industry Booths
Keynote 2
10:00 – 10:30
10:30 – 11:00
Morning Tea
11:00 – 11:30
11:30 – 12:00
Industry Booths
Art Exhibit
Presentations
12:00 – 12:30
12:30 – 14:00
Industry Booths
Panel 2
15:00 – 15:30
15:30 – 16:00
Afternoon Tea
16:00 – 16:30
16:30 – 17:00
17:00 – 17:30
16
Oral 8
Poster 3 – Full/BNI
Papers and TOMM
Highlighted Papers
Oral 11
Award Ceremony and SIGMM Business
LUNCH
14:00 – 14:30
14:30 – 15:00
Poster 3 – Full/BNI
Papers and TOMM
Highlighted Papers
ACM Multimedia 2015 Conference
P7
P8
P9
P10
P11
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
10:30 – 11:00
11:00 – 11:30
11:30 – 12:00
Oral 9
Oral 10
Art Exhibit
Art Exhibit
Oral 12
Oral 13
Art Exhibit
Art Exhibit
12:00 – 12:30
12:30 – 14:00
14:00 – 14:30
14:30 – 15:00
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
Exchange
Meeting
17:00 – 17:30
ACM Multimedia 2015 Conference
17
Program at a Glance (continued)
Workshops – Friday 30 October
Auditorium Foyer
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
10:30 – 11:00
11:30 – 12:00
12:00 – 12:30
14:00 – 14:30
14:30 – 15:00
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
18
P7
MMCommons
– Multimedia
COMMONS
ImmersiveME –
Immersive Media
Experiences
CrowdMM –
Crowdsourcing for
Multimedia
MMCommons
– Multimedia
COMMONS
ImmersiveME –
Immersive Media
Experiences
CrowdMM –
Crowdsourcing for
Multimedia
MMCommons
– Multimedia
COMMONS
ImmersiveME –
Immersive Media
Experiences
CrowdMM –
Crowdsourcing for
Multimedia
MMCommons
– Multimedia
COMMONS
ImmersiveME –
Immersive Media
Experiences
CrowdMM –
Crowdsourcing for
Multimedia
BREAK
13:30 – 14:00
15:00 – 15:30
P6
Morning Tea
11:00 – 11:30
12:30 – 13:30
Auditorium
Welcome Tea/Coffee
Afternoon Tea
ACM Multimedia 2015 Conference
P8
P9
P10
P11
8:30 – 9:00
9:00 – 9:30
9:30 – 10:00
10:00 – 10:30
HCMC –
Computational
Models of Social
Interactions
ASM – Affect
and Sentiment in
Multimedia
SLAM – Speech,
Language and Audio
in Multimedia
HuEvent – Humancentered Event
Understanding from
Multimedia
HCMC –
Computational
Models of Social
Interactions
ASM – Affect
and Sentiment in
Multimedia
SLAM – Speech,
Language and Audio
in Multimedia
HuEvent – Humancentered Event
Understanding from
Multimedia
HCMC –
Computational
Models of Social
Interactions
ASM – Affect
and Sentiment in
Multimedia
SLAM – Speech,
Language and Audio
in Multimedia
HCMC –
Computational
Models of Social
Interactions
ASM – Affect
and Sentiment in
Multimedia
SLAM – Speech,
Language and Audio
in Multimedia
10:30 – 11:00
11:00 – 11:30
11:30 – 12:00
12:00 – 12:30
12:30 – 13:30
13:30 – 14:00
14:00 – 14:30
14:30 – 15:00
15:00 – 15:30
15:30 – 16:00
16:00 – 16:30
16:30 – 17:00
ACM Multimedia 2015 Conference
19
Keynotes
Tuesday October 27
KEYNOTE 1 Time:
9:00 – 10:30
Location:Auditorium
Speaker:
Judy Kay (The University of Sydney, Australia)
Title:
Harnessing Big Personal Data, with Scrutable User
Modelling for Privacy and Control
Chair:
Alan Smeaton (Dublin City University, Ireland)
Abstract
My work aims to enable people to harness, control and manage their big personal data. This is
challenging because people are generating vast, and growing, collections of personal data. That data
is captured by a rich personal digital ecosystems of devices, some worn or carried, and others are
fixed or embedded in the environment. Users explicitly store some data but systems also capture
the user’s digital footprints, ranging from simple clicks and touches, to images, audio and video. This
personal data resides in a quite bewildering range of places, from personal devices to cloud stores, in
multitudes of silos.
Big personal data differs from the scientific big data in important ways. Because it is personal, it
should be handled in ways that enable people to ensure it is managed and used as they wish. It may
be of modest size compared with scientific big data, but people consider their data stores as big,
because they are complex and hard to manage.
A driving goal for my research has been to tackle the challenges of big personal data by creating
infrastructures, representations and interfaces that enable a user to scrutinize and control their
personal data in a scrutable user model.
One important role for users models is personalisation, where the user model is a dynamic set
of evidence-based beliefs about the user. This is the foundation for personalization, ranging from
recommenders to teaching systems. User models may represent anything from the user’s attributes
to their knowledge, beliefs, goals, plans and preferences. Some user modeling evidence comes
directly from the user; for example, people typically provide dating sites with rich (if not entirely
accurate) descriptions of themselves and about the people they believe that would like. Much
commercial user modeling evidence comes from observing the user; for example, a personalized
teaching system observes the learner’s interactions, as they use learning resources and tackle
20
ACM Multimedia 2015 Conference
problem and from this data the system infers what the learner knows. Typically, a user model refines
raw data about the user and combines it with other knowledge. For example, teaching systems make
use of a knowledge model of the domain and recommenders use collaborative filters based on user
models of many people. A scrutable user model is designed to enable people to scrutinize their own
user model, the processes used to form it and the ways that it is used.
A second important role for the user model is as an independent first class citizen; user models can
be valuable in their own right, independently of whether they are used by any personalised system.
Such user models have the potential to support diverse forms of learning. This is because they can
mirror salient aspects of the user over the long term, and when there is a suitable interface to these
models, they can provide a valuable resource. In education, this is described in terms of important
self-regulated learning processes, such as reflection, self-monitoring and planning. Some broader
uses are central to the Quantified Self movement.
The talk presents a series of four linked case studies of my work.
Bio
Judy Kay is Professor of Computer Science. She leads the multi-disciplinary Human Centred
Technology Research Cluster, based in the Faculty of Engineering and Information Technologies at
the University of Sydney, Australia. Her own lab, CHAI (Computer Human Adapted Interaction) aims
to create new technologies for human computer interaction (HCI). Her personalisation research
has created the Personis user modelling framework. This is a unified mechanism for keeping and
managing people’s long-term personal data from diverse sources. This is the foundation for build- ing
personalised systems. Personis models are distinctive in that they were designed to be scrutable,
because interfaces enable the user to scrutinise their user model and personalisation processes
based on it. In learning contexts, she has created interfaces for Open Learner Models that make
this personal data available in useful forms for long-term learning and self-monitoring. In other
recent interface research, her team has created the Cruiser Natural User Interaction (NIU) software
framework. This provides new ways for people to make use of large interactive tabletops and wall
displays. By mining the digital footprints of such interaction, this research is creating new ways for
people to learn to collaborate, and to learn and work more collaboratively.
She has extensive publications in venues such as the conferences Ubicomp, Pervasive, Computer
Human Interaction (CHI), Interactive Tabletops and Surfaces User Modeling (UM, AH, UMAP), AIED
and journals, such as IEEE Transactions on Knowledge and Data Engineering, International Journal
of Artificial Intelligence in Education (IJAIED), User Modeling and User-Adapted Interaction (UMUAI),
IEEE Transactions on Learning Technologies (IEEE TLT), Personal and Ubiquitous Computing,
Communications of the ACM, Computer Science Education.
ACM Multimedia 2015 Conference
21
Thursday October 29
KEYNOTE 2 Time:
9:00 – 10:30
Location:Auditorium
Speaker:
Zhengyou Zhang (Microsoft Research, USA)
Title:
Vision-enhanced Immersive Interaction and Remote
Collaboration with Large Touch Displays
Chair:
Xiaofang Zhou (The University of Queensland,
Australia)
Abstract
Large displays are becoming commodity, and more and more, they are touch-enabled. In this
keynote, we describe a system called ViiBoard (Vision-enhanced Immersive Interaction with touch
Board) that enables natural interaction and immersive remote collaboration with large touch displays
by adding a commodity color plus depth sensor. It consists of two parts.
The first part is called VTouch that augments touch input with visual understanding of the user to
improve interaction with a large touch-sensitive display such as Microsoft Surface Hub. An RGBD
sensor such as Microsoft Kinect adds the visual modality and enables new interactions beyond
touch. Through visual analysis, the system understands where the user is, who the user is, and what
the user is doing even before the user touches the display. Such information is used to enhance
interaction in multiple ways. For example, a user can use simple gestures to bring up menu items
such as color palette and soft keyboard; menu items can be shown where the user is and can follow
the user; hovering can show information to the user before the user commits to touch; the user
can perform different functions (for example writing and erasing) with different hands; and the user’s
preference profile can be maintained, distinct from other users. User studies are conducted and the
users very much appreciate the value of these and other enhanced interactions.
The second part is called ImmerseBoard. ImmerseBoard is a system for remote collaboration through
a digital whiteboard that gives participants a 3D immersive experience, enabled by an RGBD sensor
mounted on the side of a large touch display (the same setup as in VTouch). Using 3D processing
of the depth images, life-sized rendering, and novel visualizations, ImmerseBoard emulates writing
side-by-side on a physical whiteboard, or alternatively on a mirror. User studies involving three
tasks show that compared to standard video conferencing with a digital whiteboard, ImmerseBoard
provides participants with a quantitatively better ability to estimate their remote partners’ eye gaze
direction, gesture direction, intention, and level of agreement. Moreover, these quantitative capabilities
translate qualitatively into a heightened sense of being together and a more enjoyable experience.
ImmerseBoard’s form factor is suitable for practical and easy installation in homes and offices.
22
ACM Multimedia 2015 Conference
Bio
Zhengyou Zhang received the B.S. degree in electronic engineering from Zhejiang University,
Hangzhou, China, in 1985, the M.S. degree in computer science from the University of Nancy, Nancy,
France, in 1987, and the Ph.D. degree in computer science and the Doctorate of Science (Habilitation
à diriger des recherches) from the University of Paris XI, Paris, France, in 1990 and 1994, respectively.
He is a Principal Researcher with Microsoft Research, Redmond, WA, USA, and the Research
Manager of the “Multimedia, Interaction, and Experiences” group. Before joining Microsoft Research
in March 1998, he was a Senior Research Scientist with INRIA (French National Institute for Research
in Computer Science and Control), France. In 1996-1997, he spent a one-year sabbatical as an
Invited Researcher with the Advanced Telecommunications Research Institute International (ATR),
Kyoto, Japan. He has published over 200 papers in refereed international journals and conferences,
and has coauthored the following books: 3-D Dynamic Scene Analysis: A Stereo Based Approach
(Springer-Verlag, 1992); Epipolar Geometry in Stereo, Motion and Object Recognition (Kluwer, 1996);
Computer Vision (Chinese Academy of Sciences, 1998, 2003, in Chinese); Face Detection and
Adaptation (Morgan and Claypool, 2010), and Face Geometry and Appearance Modeling (Cambridge
University Press, 2011). He is an inventor of more than 100 issued patents. He has given a number of
keynotes in international conferences and invited talks in universities.
Dr. Zhang is an IEEE Fellow and an ACM Fellow. He is the Founding Editor-in-Chief of the IEEE
Transactions on Autonomous Mental Development, and has served on the editorial board of IEEE
TPAMI, IEEE TCSVT, IEEE TMM, IJCV, IJPRAI, MVA, among others. He has served as a program
chair, a general chair, and a program committee member for numerous international conferences in
the areas of computer vision, audio and speech signal processing, multimedia, human-computer
interaction, and autonomous mental development. He is serving as a General Chair of International
Conference on Multimodal Interaction (ICMI) 2015, and a General Chair of IEEE Conference on
Computer Vision and Pattern Recognition (CVPR) 2017. He received the IEEE Helmholtz Test of Time
Award at ICCV 2013 for his paper published in 1999 on camera calibration, now known as Zhang’s
method.
ACM Multimedia 2015 Conference
23
Art Exhibit
Tuesday 27 October
Time:
18:00 – 20:00
Location:
P10 – P11
Topic:
Opening and Welcome Reception
Wednesday 28 October
Time:
11:00 – 17:30
Location:
P10 – P11
Topic:
Art Exhibit
Thursday 29 October
Time:
11:00 – 12:30
Location:
Auditorium
Topic:
Art Exhibit Presentations
Time:
11:00 – 15:30
Location:
P10 – P11
Topic:
Art Exhibit
Using Handmade Controllers for Interactive Projection Mapping
Alinta K. Krauth (Griffith University, Australia)
3D Printing and Camera Mapping: Dialectic of Virtual and Reality
He-Lin Luo, Yi-Ping Hung (National Taiwan University) I-Chun Chen (Taipei National University of the
Arts, Taiwan)
Drag A Star – the Social Media in Outer Space
James She (Hong Kong University of Science & Technology) Cameron Ng (JM Network, Hong Kong)
Desmond Leung (Desmond Leung Media Arts, Hong Kong)
Disturbed System: Recreating Sculptor’s Experience of Their Medium With Haptics and
Generated Sound
Oksana Krzyhanivska, Simon Fay, Jeffrey E. Boyd (University of Calgary, Canada)
The Real Time Rolling Shutter
David S. Monaghan, Noel E. O’Connor (Dublin City University, Ireland) Anne Cleary, Denis Connolly
(Independent artists, France)
24
ACM Multimedia 2015 Conference
Monday 26 October
Tutorials
ACM Multimedia 2015 Tutorials will address the state-of-the-art research and developments
regarding all aspects of multimedia, and will be of interest to the entire multimedia community,
from novices in the world of multimedia to the most seasoned researchers, from people working in
academia to industry professionals.
Half Day Tutorials (1, 2, 3, 6, 7, 8)
TUTORIAL 1
Time:
9:00 – 12:30
Location:
P7
Topic:
VM Hub: Building Cloud Service and Mobile Application for
Image/Video/Multimedia Services
Speaker:
Jin Li
This is an advanced tutorial intended for professionals, researchers and students who are interested
to build: 1) image/video/multimedia recognition services that are hosted in the cloud, and 2)
cross platform app (on iOS, android, and windows phone) that consumes their own image/video/
multimedia recognition services or services provided by other parties. The class will leverage VHub,
a largely open sourced image/video/multimedia hub hosted in Azure. We expect that the audience to
have basic knowledge of multimedia programming.
Dr. Jin Li is a Partner Research Manager of the Cloud Computing and Storage (CCS) group in
Microsoft Research. He leads a small yet high performance group of researchers engaged research
in an end-to-end approach, and believes that the ultimate milestone of cool research is a product
of significant impact. He and his group has architected (and in many cases written the code for) the
solution they have shipped in Microsoft. His work on Local Reconstruction Code (LRC) in Windows
Azure Storage has led to hundreds of millions of dollars of savings for Microsoft, a Best Paper
Award at USENIX ATC 2012 and a 2013 Microsoft Technical Community Network Storage Technical
Achievement Award. LRC is also shipped in Windows Storage Space in Windows 8 and Windows
Server 2012 R2. His group has architected and implemented the Primary Data Deduplication feature
in Windows Server 2012 and End-to-End Deduplication for Storage Virtualization in Windows Server
2012 R2, which is among top 3 features for Windows File Server introduced at Windows Server
2012, received rave reviews from press, with evidence that some customers upgrading to Windows
Server 2012 for the primary data deduplication feature only. His group has assisted to architect and
implement the RemoteFX for WAN feature in Windows 8 and Windows Server 2012, which provides
fast and fluid user experience in a remote session running over any WAN and wireless networks.
ACM Multimedia 2015 Conference
25
Monday 26 October
Dr. Li was the recipient of Young Investigator Award from Visual Communication and Image
Processing’98 (VCIP) in 1998, and the ICME 2009 Best Paper Award. He was the General Chair of
PV2009, the lead Program Chair of ICME 2011. He currently serves as ICME steering committee
chair and a TPC Co-Chair of ACM Multimedia 2016. He is an IEEE Fellow.
TUTORIAL 2
Time:
13:30 – 17:00
Location:
P7
Topic:
Interactive Video Search
Speakers:
Klaus Schoeffmann, Frank Hopfgartner
With an increasing amount of video data in our daily life, the need for content-based search in videos
increases as well. Though a lot of research has been spent on video retrieval tools and methods,
which allow for automatic search in videos through content-based queries, still the performance of
automatic video retrieval is far from optimal. One problem of automatic video retrieval is the fact that
the actual search process is performed by the video retrieval engine, which is a black box for the user.
More importantly, there are situations where the common query-and-browse-results approach cannot
be employed, for example when users are not able to formulate their search needs through a query –
or when they simply want to browse the content without any concrete query in mind. Interactive video
search tools provide a more flexible way of content-based search in videos. They provide various
content interaction features and give full control of the search process to the user, who will know best
which features to use and how, in order to solve a search problem. In this tutorial we will discuss (i)
proposed solutions for improved video content navigation, (ii) typical interaction of content-based
querying features, and (iii) advanced video content visualization methods. Moreover, we will discuss
and demonstrate interactive video search systems and ways to evaluate their performance.
Klaus Schoeffmann is Associate Professor at the Institute of Information Technology (ITEC) at
Klagenfurt University, Austria, where he also received his Ph.D. degree in Computer Science. His
current research focuses on Human-Computer-Interaction with multimedia data (e.g., image and
video browsing), mobile multimedia, and video processing. He has co-authored more than 60
publications on various topic in multimedia and he has co-organized international conferences,
special sessions and workshops (e.g., MMM2012, CBMI 2013, VisHMC 2014, MMC 2014, and
MMC 2015). He is organizer of the Video Browser Showdown evaluation competition (VBS). Further,
he is an editorial board member of the Springer International Journal on Multimedia Tools and
Applications (MTAP) and a steering committee member of the International Conference on MultiMedia
Modelling (MMM). Additionally, he is member of the IEEE and the ACM and a regular reviewer for
international conferences and journals in the field of Multimedia. Prof. Schoeffmann teaches various
courses in computer science (including interactive multimedia applications, media technology,
multimedia systems, operating systems, distributed systems).
Frank Hopfgartner is Lecturer in Information Studies at University of Glasgow. He received a PhD
in Computing Science from the same university with a thesis on multimedia information retrieval. His
research to date can be placed in the intersection of interactive systems and multimedia content
access. He co-authored over 100 publications in above mentioned research elds, including a
book on smart information systems, various book chapters and papers in peer-reviewed journals,
26
ACM Multimedia 2015 Conference
Monday 26 October
conferences and workshops. Frank co-organizes LifeLog, a shared task at NTCIR-12 on different
methods of retrieval and access of multimedia lifelogging data. Besides, he has held various roles in
the organization of multimedia conferences (MMM’17, MeasuringBehaviour’16, MMM’14, ICMR’14,
MMM’12) and has co-organized workshops, sessions and tutorials at major venues such as SIGIR,
RecSys, ICME, Ubicomp, ECIR, Hypertext, iConference and IIiX. Moreover, he was involved in the
organization of a summer school on multimedia semantics (SSMS’07). He is a regular reviewer of
various renowned journals and has been PC member of international conferences (e.g., SIGIR, MM,
ESWC, WWW, RecSys) and workshops.
TUTORIAL 3
Time:
9:00 – 12:30
Location:
P8
Topic:
Learning Knowledge Bases for Multimedia in 2015
Speakers:
Lexing Xie, Haixun Wang
Knowledge acquisition, representation, and reasoning has been one of the long-standing challenges
in artificial intelligence and related application areas. Only in the past few years, massive amounts
of structured and semi-structured data that directly or indirectly encode human knowledge became
widely available, turning the knowledge representation problems into a computational grand
challenge with feasible solutions in sight. The research and development on knowledge bases is
becoming a lively fusion area among web information extraction, machine learning, databases and
information retrieval, with knowledge over images and multimedia emerging as another new frontier
of representation and acquisition. This tutorial aims to present a gentle overview of knowledge bases
on text and multimedia, including representation, acquisition, and inference. In particular, the 2015
edition of the tutorial will include recent progress from several active research communities: web,
natural language processing, and computer vision and multimedia.
Lexing Xie is Senior Lecturer of Computer Science at the Australian National University. She was
a research staff member at IBM T.J. Watson Research Center in New York from 2005 to 2010, and
adjunct assistant professor at Columbia University 2007–2009. She received B.S. from Tsinghua
University, China, and M.S. and Ph.D. degrees from Columbia University, all in Electrical Engineering.
Her research interests are in applied machine learning, multimedia, social media. Lexing’s research
has received six best student paper and best paper awards between 2002 and 2015, and a Grand
Challenge Multimodal Prize at ACM Multimedia 2012. Her service roles include associate editorship
for both the IEEE and ACM Transactions on Multimedia, and the program and organizing committees
of major multimedia, machine learning, web and social media conferences.
Haixun Wang is a research scientist at Facebook. Before joining Facebook, he was a research
scientist at Google Research; senior researcher at Microsoft Research Asia in Beijing, China, where
he manages the group of Data Management, Analytics, and Services; he had also been a research
staff member at IBM T. J. Watson Research Center for 9 years. Haixun Wang has published more
than 120 research papers in referred international journals and conference proceedings. He is on the
editorial board of Distributed and Parallel Databases (DAPD), IEEE Transactions of Knowledge and
Data Engineering (TKDE), Knowledge and Information System (KAIS), Journal of Computer Science
and Technology (JCST). He is PC co-Chair of WWW 2013 (P&E), ICDE 2013 (Industry), CIKM 2012,
ACM Multimedia 2015 Conference
27
Monday 26 October
ICMLA 2011, WAIM 2011. Haixun Wang got the ICDM 10-Year Highest Impact Paper Award in 2014,
ER 2008 best paper award (DKE 25 year award), ICDM 2009 Best Student Paper run-up award, and
ICDE 2015 Best Paper Award.
TUTORIAL 6
Time:
13:30 – 17:00
Location:
P8
Topic:
An Introduction to Arts and Digital Culture inside Multimedia
Speakers:
David A. Shamma, Daragh Byrne
The Arts and Digital Culture program has offered a high quality forum for the presentation of
interactive and arts-based multimedia applications at the annual ACM Multimedia conference for
over a decade. This tutorial will explore the evolution of this program as a guide to new authors
considering future participation in this program. By surveying both past technical and past exhibited
contributions, this tutorial will offer guidance to artists, researchers and practitioners on success at
this multifaceted, interdisciplinary forum at ACM Multimedia.
David A. Shamma (Yahoo! Labs, USA) is a senior research scientist and head of the HCI Research
group at Yahoo! Labs and Flickr. His personal research investigates synchronous environments and
connected experiences both online and in-the-world. Focusing on creative expression and sharing
frameworks, he designs and prototypes systems for multimedia-mediated communication, as well
as, develops targeted methods and metrics for understanding how people communicate online in
small environments and at web scale. Ayman is the creator and lead investigator on the Yahoo! Zync
project, is the scientific liaison to Flickr, and is on the iSchool at Berkeley’s Data Science Advisory
board. Additionally, Ayman serves on the ACM MM Steering Committee, the ACM TVx Steering
Committee, and is a co-editor for Arts & Digital Culture for SIGMM. He recently was a Visiting Senior
Research Fellow at the National University of Singapore’s CUTE Center in the Interactive Digital Media
Institute. In the past he has worked at the Medill School of Journalism and NASA Ames Research
Center. He has a Ph.D. in Computer Science from Northwestern University and a M.S./B.S. in
Computer Science from the University of West Florida.
Daragh Byrne is Intel Special Faculty for Physical Computing, Responsive Environments and
Emerging Media within the IDeATe Network and at School of Architecture at Carnegie Mellon
University, where he explores the design of experiential media systems through process-oriented
methods. Both at CMU and in his previous role as an Assistant Research Professor at Arizona State
University’s School of Arts, Media and Engineering, he manages the NSF Funded XSEAD project. He
also leads the recently launched the MakeSchools.org effort to catalog Making in higher education.
He defended his PhD at Dublin City University in August 2011, holds an M.Res. degree in Design
and Evaluation of Advanced interactive Systems from Lancaster University and a BSc. in Computer
Applications from DCU. During his research career, he has published over 40 scientific papers and his
doctoral work represents a first of its kind exploration where long-term multimodal lifelog collections
were established to explore the creation of personal digital stories. This research interest continues
with a current focus on process-oriented design research into experience capture, participatory
documentation, and in particular, digital curation.
28
ACM Multimedia 2015 Conference
Monday 26 October
TUTORIAL 7
Time:
9:00 – 12.30
Location:
P11
Topic:
Human-centric images and videos analysis
Speakers:
Si Liu, Liang Lin, Bingbing Ni
This tutorial reviews recent progresses in human-centric images and videos analysis: 1) fashion
analysis: parsing, attribute prediction and retrieval; 2) action analysis: discriminative feature selection,
pooling and fusion; 3) person verification: cross-domain person verification via learning a generalized
similarity measure, and bit scalable deep hashing with regularized similarity learning.
Dr. Si Liu is now an Associate Professor in Institute of Information Engineering, Chinese Academy
of Sciences. She used to be a Research Fellow at the Department of Electrical and Computer
Engineering, National University of Singapore (NUS). She obtained PhD degree from Institute of
Automation, Chinese Academy of Sciences (CASIA) in 2012. She obtained Bachelor degree from
Experimental Class of Beijing Institute of Technology (BIT). Her current research interests include
attribute prediction, object detection andimage parsing. She is also interested in the applications,
such as makeup and clothes recommendation, online product retrieval. She received the Best Paper
Awards from ACM MM’13, Best Demo Awards from ACM MM’12.
Liang Lin is a Professor with the School of AdvancedComputing, Sun Yat-Sen University (SYSU),
China. He received the B.S. and Ph.D. degrees from the Beijing Institute of Technology (BIT),
Beijing, China, in 1999 and 2008, respectively. From 2006to 2007, he was a joint Ph.D. student
with theDepartment of Statistics, University of California, Los Angeles (UCLA). His Ph.D. dissertation
was achieved the China National Excellent Ph.D. Thesis Award Nomination in 2010. He was a
Post-DoctoralResearch Fellow with the Center for Vision, Cognition, Learning, and Art of UCLA.
His research focuses on new models, algorithms and systems for intelligent processing and
understanding of visualdata such as images and videos. He has published more than 70 papers intop
tier academic journals and conferences. He was supported by several promotive programs or funds
for his works, such as “Program for New Century Excellent Talents” of Ministry of Education (China)
in 2012, and Guangdong NSFs for Distinguished Young Scholars in 2013. He received the Best
PaperRunners-Up Award in ACM NPAR 2010, Google Faculty Award in 2012,and Best Student Paper
Award in IEEE ICME 2014. He has served as anAssociate Editor for Neurocomputing and The Visual
Computer.
Dr. Bingbing Ni received his B.Eng. degree in Electrical Engineering from Shanghai Jiao Tong
University (SJTU), China in 2005 and obtained his Ph.D. from National University of Singapore
(NUS), Singapore in 2011. Dr. Ni is currently a research scientist in Advanced Digital Sciences
Center, Singapore. His research interests are in the areas of computer vision, machine learning and
multimedia. Dr. Ni worked in Microsoft Research Asia, Beijing as a research intern in 2009. He also
worked as a software engineer intern in Google Inc., Mountain View, CA in 2010. He received the Best
Paper Award from PCM’11 and the Best Student Paper Award from PREMIA’08. He won the first
prize in International Contest on Human Activity Recognition and Localization (HARL) in conjunction
with International Conference on Pattern Recognition 2012, and the second prize in ChaLearn Action
Recognition Challenge in conjunction with European Conference on Computer Vision (ECCV) 2014,
respectively.
ACM Multimedia 2015 Conference
29
Monday 26 October
TUTORIAL 8
Time:
13:30 – 17:00
Location:
P11
Topic:
User-centric Cross-OSN Multimedia Computing
Speaker:
Jitao Sang
The explosion of social media has led to various Online Social Networking (OSN) services. Today’s
typical netizens are using a multitude of OSN services. Exploring the user-contributed cross-OSN
heterogeneous data is critical to connect between the separated data island and facilitate value
mining from big social multimedia. From the perspective of content analysis, understanding the
association among heterogeneous cross-OSN data is fundamental to advanced social media
analysis and applications. From the perspective of user modeling, exploiting the available user data
on different OSNs contributes to an integrated online user profile and thus improved customized
social media services. This tutorial will introduce several pilot works on two basic tasks on cross-OSN
multimedia computing: (1) From users: cross-OSN knowledge association mining and (2) For users:
cross-OSN user modeling and collaborative applications.
Jitao Sang is assistant professor in National Laboratory of Pattern Recognition at Institute of
Automation, Chinese Academy of Sciences (CAS). He graduated his PhD from CAS with the highest
honor, the special prize of CAS president scholarship. His research interest is in social multimedia
computing, where the recent research on user-centric social multimedia computing has attracted
increasing attentions, with award-winning publications in the prestigious multimedia conferences
(best paper finalist in MM2012 & MM2013, best student paper in MMM2013, best student paper in
ICMR2015). So far, he has authored one book, filed three patents, co-authored more than 40 peerreferenced papers in multimedia-related journals and conferences. He is program co-chair in PCM
2015, ICIMCS 2015, publicity chair in MMM 2015, publication chair in ICIMCS 2013, 2014, special
session organizer in ICME2015, MMM2013, ICIMCS 2013, and program committee member in many
conferences (MM2013, MM2014, CIKM2014, etc.). He is associate editor in Neurocomputing, guest
editor in MMSJ and MTA. He is tutorial speaker at MM 2014, MMM 2015, ICME 2015 and ICMR
2015.
30
ACM Multimedia 2015 Conference
Monday 26 October
Full Day Tutorials (4, 5)
TUTORIAL 4
Time:
9:00 – 17:00
Location:
P9
Topic:
Image Tag Assignment, Refinement and Retrieval
Speakers:
Xirong Li, Tiberio Uricchio, Lamberto Ballan, Marco Bertini, Cees G.M.
Snoek, Alberto Del Bimbo
This tutorial focuses on challenges and solutions for content-based image annotation and retrieval
in the context of online image sharing and tagging. We present a unified review on three closely
linked problems, i.e., tag assignment, tag refinement, and tag-based image retrieval. We introduce
a taxonomy to structure the growing literature, understand the ingredients of the main works, clarify
their connections and difference, and recognize their merits and limitations. Moreover, we present an
open-source testbed, with training sets of varying sizes and three test datasets, to evaluate methods
of varied learning complexity. A selected set of eleven representative works have been implemented
and evaluated. During the tutorial we provide a practice session for hands on experience with the
methods, software and datasets. For repeatable experiments all data and code are online at
http://www.micc.unifi.it/tagsurvey
Xirong Li is currently an assistant professor at the Key Lab of Data Engineering and Knowledge
Engineering, Renmin University of China. He received Bachelor (2005) and Master (2007) degrees
from Tsinghua University, and the PhD degree from University of Amsterdam (2012), all in computer
science. His research focuses on multimedia retrieval. He has been awarded the ACM SIGMM Best
PhD Thesis Award 2013, the IEEE Transactions on Multimedia Prize Paper Award 2012, the Best
Paper Award of the ACM CIVR 2010, and PCM 2014 Outstanding Reviewer Award. He has served
as publicity co-chair for ACM ICMR 2013 and publication co-chair for ACM ICMR 2015.
Tiberio Uricchio is currently a Ph.D. candidate in computer science at the Media Integration and
Communication Centre (MICC), University of Florence, Italy. He received his B.S. and M.S. degrees
both in computer engineering from the University of Florence, Italy in 2009 and 2012, respectively.
His research interests include image and video understanding, social media analysis and machine
learning.
Lamberto Ballan is currently a postdoctoral researcher at Stanford University, supported by a
prestigious Marie Curie Fellowship from the European Commission. He received the Laurea degree
in computer engineering in 2006 and the PhD degree in computer science in 2011, both from
the University of Florence, Italy. He was also a visiting scholar at the Signal and Image Processing
department at Telecom Paristech, in 2010. His research interests lie at the intersection of multimedia
and computer vision, particularly in the areas of image/video understanding and social media
analysis. His work was conducted in the context of several EU and national projects, and his results
have led to more than 30 publications in international journals and conferences, mainly in multimedia
and image analysis. He has been awarded the best paper award by the ACM-SIGMM Workshop
on Social Media in 2010. He was also the lead organizer of the Web-scale Vision and Social Media
Workshops at ECCV 2012 and CVPR 2014.
ACM Multimedia 2015 Conference
31
Monday 26 October
Marco Bertini is currently assistant Professor at the University of Florence, Italy. He is working at the
Media Integration and Communication Center of the University of Florence. His interests are focused
on image and video analysis, addressing semantic annotation, retrieval and transcoding. He is author
of 20 journal papers and more than 90 peer-reviewed conference papers. He has been involved in 9
EU research projects as WP coordinator and researcher. Dr. Bertini is member of the editorial board
of IEEE Transactions on Multimedia, and has been awarded the best paper award by the ACMSIGMM Workshop on Social Media in 2010. He is co-organizer of the Web-scale Vision and Social
Media Workshops at ECCV 2012 and CVPR 2014.
Cees G.M. Snoek is currently an Associate Professor in the Intelligent Systems Lab at the University
of Amsterdam and a Principal Engineer at Qualcomm Research Netherlands. He was previously
at Carnegie Mellon University, USA, UC Berkeley, and head of R&D at University spin-off Euvision
Technologies (acquired by Qualcomm). His research interests focus on video and image retrieval.
Dr. Snoek is the lead researcher of the award-winning MediaMill Semantic Video Search Engine,
which is the most consistent top performer in the yearly NIST TRECVID evaluations. Dr. Snoek is a
senior member of IEEE and ACM and member of the editorial boards for IEEE MultiMedia and IEEE
Transactions on Multimedia. Cees is recipient of an NWO Veni award, a Fulbright Junior Scholarship,
an NWO Vidi award, and the Netherlands Prize for ICT Research. Several of his Ph.D. students and
Post-docs have won awards, including the IEEE Transactions on Multimedia Prize Paper Award, the
SIGMM Best Ph.D. Thesis Award, and Best Paper Award of ACM Multimedia. He is general co-chair
of ACM Multimedia 2016.
Alberto Del Bimbo is full professor at the University of Florence, Italy, where he is the Director of
MICC – Media Integration and Communication Center, leading a research team on cutting-edge
solutions in the fields of computer vision, multimedia content analysis, indexing and retrieval, and
multimedia and multimodal interactivity. He is the author of more than 300 research papers that
appeared in the most pretigious scientific journals and conference proceedings. He is a Founding
Member of the ACM EuroMM, the European Chapter of ACM SIGMM, a Member of the ACM
Steering Committee of ACM Int’l Conf. on Multimedia and ACM Int’l Conf. on Multimedia Retrieval
and served as Associate Editor of some of the most important journals in the field, among which
Pattern Recognition, IEEE Trans. on Pattern Analysis and Machine Intelligence and IEEE Trans. on
Multimedia. He was the General Chair of ECCV’12, the European Conf. on Computer Vision, ACM
ICMR’11, the Int’l Conf. on Multimedia Retrieval, ACM MM’10, the Int’l Conf. on Multimedia, ACM
MIR’08, the Int’l Conf. on Multimedia Information Retrieval, IEEE ISM’08, the Int’l Symposium on
Multimedia, and IEEE ICMCS’99, the Int’l Conf. on Multimedia Computing & Systems.
TUTORIAL 5
Time:
9:00 – 17:00
Location:
P10
Topic:
Emotional and Social Signals for Multimedia Research
Speakers:
Hayley Hung, Hatice Gunes
A challenge for human-centred multimedia is the analysis of human communicative behaviour
in multimedia content when considering especially the spontaneous non-verbal signals that are
32
ACM Multimedia 2015 Conference
Monday 26 October
generated by humans when interacting with each other. These signals require a different approach
to multimedia computing where the methods developed need findings from other disciplines such
as social and behavioural psychology, affective computing and social signal processing. This tutorial
aims to address the gaps in understanding between these disciplines, providing core knowledge of
each domain and to disseminate basic foundational concepts in emotional and social signal research
in a very practical and interactive manner.
Hayley Hung is an Assistant Professor and Delft Technology Fellow in the Pattern Recognition
and Bioinformatics group at TU Delft, The Netherlands, since 2013. Between 2010–2013, she
held a Marie Curie Intra-European Fellowship at the Intelligent Systems Lab at the University of
Amsterdam. Between 2007–2010, she was a post-doctoral researcher at Idiap Research Institute in
Switzerland. She obtained her PhD in Computer Vision from Queen Mary University of London, UK
in 2007 and her first degree from Imperial College, UK in Electrical and Electronic Engineering. Her
research interests are in social computing, social signal processing, machine learning, and ubiquitous
computing. She is local arrangements chair for ACM MM 2016, Workshop co-chair ACM ICMI 2015,
area chair of the area on emotional and social signals at ACM MM (2014–2015), co-panel organiser
for the panel on Emotional and Signals in Multimedia (ACM MM 2014), Doctoral Symposium co-chair
ACM MM (2013). She has organized workshops on human behavior understanding (InterHUB ( AmI
2011), Measuring Behaviour in open spaces (MB 2012), HBU (ACM MM 2013). She is also a special
issue guest editor for ACM Transactions on Interactive Intelligent Systems. She has received first prize
in the IET Written Premium competition 2009, was nominated for outstanding paper at ICMI 2011,
and was named outstanding reviewer at ICME 2014.
Hatice Gunes is a Senior Lecturer (Associate Professor) at Queen Mary University of London, leading
the Affective and Human Computing Lab. Her research interests lie in the multidisciplinary areas of
affective computing and social signal processing, focusing on automatic analysis of emotional and
social behavior and human aesthetic canons, multimodal interaction, computer vision, machine
learning, and human-computer and human-robot interactions. She published over 75 technical
papers in these areas (Google scholar citations>1700, H-index=20) and was a recipient of awards
for Outstanding Paper (IEEE FG’11), Quality Reviewer (IEEE ICME’11) and Best Demo (IEEE ACII’09).
She serves as Associate Editor of IEEE Transactions on Affective Computing, on the Management
Board of Association for the Advancement of Affective Computing, and the Steering Committee of
IEEE Transactions on Affective Computing. She has also served as a Guest Editor of Special Issues
in Int’l J. of Synthetic Emotions, Image and Vision Computing, and ACM Transactions on Interactive
Intelligent Systems, and member of the Editorial Advisory Board for the Affective Computing and
Interaction Book (IGI Global, 2011), cofounder and main organizer of the EmoSPACEWorkshops at
IEEE FG’15, FG’13 and FG’11, workshop chair of MAPTRAITS’14, HBU’13 and AC4MobHCI’12, and
area chair for ACM Multimedia’ 15, ACM Multimedia’14, IEEE ICME’13, ACM ICMI’13 and ACII’13.
She has been involved as PI and Co-I in several projects funded by the Engineering and Physical
Sciences Research Council UK (EPSRC) and the British Council.
Monday 26 October
ACM Multimedia 2015 Conference
33
Monday 26 October
Workshops
Workshop:
SIGMM Inaugural Workshop on Multimedia Frontiers
– with Invited Presentations by Multimedia Rising Stars
Organizers:
Shih-Fu Chang, SIGMM Chair, Rainer Lienhart, SIGMM Vice Chair,
Nicu Sebe, SIGMM Conference Director
Time:
9:00 – 17:00
Location:
Auditorium
In celebration of the rising leadership of the multimedia community, we are launching a new SIGMM
Workshop on Multimedia Frontiers, a prestigious event exclusively reserved to highlight invited talks
by rising stars who have received PhD degree within the last 10 years and demonstrated exceptional
potential in multimedia research. The workshop will highlight oral presentations by the rising stars,
each of 20–30 minutes length, followed by comments from other senior leaders in the related fields.
Our goal is to use this event to recognize the outstanding research achievements made by the rising
members of SIGMM, and at the same time, for them to share their exciting vision with the broad
community. We expect the ignited dialogs among the rising stars, the senior members, and the
community at large will help shape the direction and inspire new ideas in the multimedia community.
This event will be freely available to all participants in ACM Multimedia Conference. We sincerely invite
everyone interested in the emerging trends and frontiers of multimedia to join us in this inaugural
endeavor!
2015 Invited Rising Star Speakers:
Cees Snoek, University of Amsterdam and Qualcomm
ChengHsin Hsu, National Tsinghua University
Peng Cui, Tsinghua University
Gerald Friedland, ICSI
Hervé Jégou, Facebook AI Research
Kuan-Ta Chen, Academia Sinica
Lexing Xie, Australia National University
Pradeep Atrey, University at Albany
Ramanathan Subramanian, ADSC
Vivek Singh, Rutgers University
Xavier Alameda-Pineda, University of Trento
Yu-Gang Jiang, Fudan University
34
ACM Multimedia 2015 Conference
Monday 26 October
Workshop:
AVEC 2015 – The 5th International Audio/Visual Emotion Challenge
and Workshop
Time:
8:30 – 17:00
Location:
P6
Session 0 – Keynote
Chair: Fabien Ringeval
8:30
AVEC’15 Keynote Talk – From Facial Expression Analysis to Multimodal Mood Analysis
Roland Göcke, University of Canberra, Australia.
Session 1 - Introduction
Chair: Roland Göcke
9:30
10:00
AV+EC 2015 Challenge Introduction,
Fabien Ringeval, Björn Schuller, Michel Valstar, Roddy Cowie, Maja Pantic, University of Passau,
Germany, Imperial College London, UK, University of Nottingham, UK, Queen’s University Belfast, UK.
Coffee Break
Session 2 – AV+EC 2015 Part 1
Chair: Michel Valstar
10:30
Ensemble Methods for Continuous Affect Recognition: Multi-modality, Temporality, and Challenges Markus Kächele, Patrick Thiam, Günther Palm, Friedhelm Schwenker and Martin Schels, University of
Ulm, Germany.
10.55
ETS System for AV+EC 2015 Challenge
Patrick Cardinal, Najim Dehak, Alessandro L. Koerich, Jahangir Alam and Patrice Boucher, École de
technologie supérieure ÉTS, Canada, Centre de recherche informatique de Montréal (CRIM), Canada,
Massachusetts Institute of Technology (MIT), USA.
11.20
Vocal Emotion Recognition with Log-Gabor Filters
Yu Gu, Eric Postma and Haixiang Lin, Tilburg center for Cognition and Communication, University of
Tilburg, Netherlands, Delft University of Technology, University of Delft, The Netherlands.
11.45
Multimodal Affective Analysis combining Regularized Linear Regression and Boosted Regression Trees
Aleksandar Milchevski, Alessandro Rozza and Dimitar Taskovski, Faculty of Electrical Engineering and
Information Technologies, Republic of Macedonia, HYERA Software, Italy.
12:10
Lunch Break
ACM Multimedia 2015 Conference
35
Monday 26 October
AVEC 2015 – The 5th International Audio/Visual Emotion Challenge and Workshop (continued)
Session 3 – AV+EC 2015 Part 2
Chair: Fabien Ringeval
14.00
An Investigation of Annotation Delay Compensation and Output-Associative Fusion for Multimodal
Continuous Emotion Prediction
Zhaocheng Huang, Ting Dang, Nicholas Cummins, Brian Stasak, Phu Le, Vidhyasaharan Sethu and Julien
Epps, The University of New South Wales, Australia.
14.25
Multi-modal Dimensional Emotion Recognition using Recurrent Neural Network
Shizhe Chen, Qin Jin, Renmin University of China, China.
14.50
Exploring the Importance of Individual Differences to the Automatic Estimation of Emotions Induced by
Music - Hesam Sagha, Eduardo Coutinho and Björn Schuller, University of Passau, Germany, Imperial
College London, UK.
15.15
Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition
Linlin Chao, Jianhua Tao, Minghao Yang, Ya Li and Zhengqi Wen, National Laboratory of Pattern
Recognition, Institute of Automation Chinese Academy of Sciences, China.
15.40
Multimodal Affective Dimension Prediction Using Deep Bidirectional Long Short-Term Memory Recurrent
Neural Networks
Lang He, Dongmei Jiang, Le Yang, Peng Wu, Ercheng Pei and Hichem Sahli, Northwestern Polytechnical
University, China, Vrije Universiteit Brussel, Belgium.
16.05
Challenge Results
16.15
Coffee Break
Session 4 – Panel Session
Chair: Michel Valstar
16.30
36
Panel Session
ACM Multimedia 2015 Conference
Tuesday 27 October
Conference Day 1
Time:
9:00 – 10.30
Location:
Auditorium
Keynote:
Harnessing Big Personal Data, with Scrutable User Modelling for
Privacy and Control
Speaker:
Judy Kay (The University of Sydney, Australia)
Chair:
Alan Smeaton (Dublin City University, Ireland)
Time:
11:00 – 12:30
Location:
Auditorium
Session:
Best Paper
Chair:
Heng Tao Shen (The University of Queensland, Australia)
Analyzing Free-standing Conversational Groups: A Multimodal Approach
Xavier Alameda-Pineda, Yan Yan (University of Trento, Italy), Elisa Ricci, Oswald Lanz (Fondazione
Bruno Kessler, Italy), Nicu Sebe (University of Trento, Italy)
An Affordable Solution for Binocular Eye Tracking and Calibration in Head-mounted
Displays
Michael Stengel, Steve Grogorick (TU Braunschweig, Germany), Elmar Eisemann (TU Delft, The
Netherlands), Martin Eisemann (TH Koeln, Germany), Marcus A. Magnor (TU Braunschweig,
Germany)
SINGA: Putting Deep Learning in the Hands of Multimedia Users
Wei Wang (National University of Singapore), Gang Chen (Zhejiang university, China), Anh Tien Tuan
Dinh, Jinyang Gao, Beng Chin Ooi, Kian-Lee Tan, Sheng Wang (National University of Singapore)
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge
Propagation
Xiangbo Shu (Nanjing University of Science and Technolog, China), Guo-Jun Qi (University of Central
Florida, USA), Jinhui Tang (Nanjing University of Science and Technology, China), Jingdong Wang
(Microsoft Research, China)
ACM Multimedia 2015 Conference
37
Tuesday 27 October
Time:
11:00 – 17:30
Location:
P9
Session:
Demo Session 1
Chair:
Alejandro Jaimes (Yahoo! Spain)
Query-by-Emoji Video Search
Spencer Cappallo, Thomas Mensink, Cees G.M. Snoek (University of Amsterdam, The Netherlands)
Dive into Remote Events: Omnidirectional Video Streaming with Acoustic Immersion
Daisuke Ochi, Kenta Niwa, Akio Kameda, Yutaka Kunita, Akira Kojima (NTT Media Intelligence
Laboratories, Japan)
Movie’s Affect Communication Using Multisensory Modalities
Joël Dumoulin, Diana Affi, Elena Mugellini, Omar Abou Khaled (HumanTech Institute, University of
Applied Sciences, Switzerland) Marco Bertini, Alberto Del Bimbo (MICC, University of Florence, Italy)
QOEYE:A Data Driven Platform for QoE Visualization and System Performance Monitoring
Chao Zhou, Lifeng Sun, Wenming Shi, Shiqiang Yang (Tsinghua University, China)
AR in Hand: Egocentric Palm Pose Tracking and Gesture Recognition for Augmented
Reality Applications
Hui Liang, Junsong Yuan, Daniel Thalmann, Nadia Magnenat Thalmann (Nanyang Technological
University, Singapore)
PPTLens: Create Digital Objects with Sketch Images
Changcheng Xiao, Liqing Zhang (Shanghai Jiao Tong University, China) Changhu Wang (Microsoft
Research)
A Multi-Modal 3D Capturing Platform for Learning and Preservation of Traditional Sports
and Games
Francois Destelle, Amin Ahmadi, Kieran Moran, Noel E. O’Connor (INSIGHT, Dublin City University,
Ireland) Nikolaos Zioulis, Anargyros Chatzitofis, Dimitrios Zarpalas, Petros Daras (ITI-CERTH, Greece)
Luis Unzueta, Jon Goenetxea, Mikel Rodriguez, Maria Linaza (Vicomtech-IK4, Spain)
Analysing Audience Response to Performing Events
Thomas Röggla, Pablo César, Chen Wang (CWI, The Netherlands)
MPEG-DASH for Low Latency and Hybrid Streaming Services
Jean Le Feuvre, Cyril Concolato, Nassima Bouzakaria, Viet-Thanh-Trung Nguyen (Telecom ParisTech,
France)
38
ACM Multimedia 2015 Conference
Tuesday 27 October
eMosic: Mobile Media Pushing through Social Emotion Sensing
Jheng-Wei Peng, Shih-Wei Sun (Taipei National University of the Arts, Taiwan) Wen-Huang Cheng,
Yi-Hsuan Yang (Academia Sinica, Taiwan)
PITAGORA: Recommending Users and Local Experts in an Airport Social Network
Andrea Ferracani, Daniele Pezzatini, Andrea Benericetti, Marco Guiducci, Alberto Del Bimbo
(Università degli Studi di Firenze – MICC, Italy)
A System for Video Recommendation using Visual Saliency, Crowdsourced and Automatic
Annotations
Andrea Ferracani, Daniele Pezzatini, Marco Bertini, Saverio Meucci, Alberto Del Bimbo (Università
degli Studi di Firenze – MICC, Italy)
A Semantic Geo-Tagged Multimedia-Based Routing in a Crowdsourced Big Data
Environment
Faizan Ur Rehman (University of Grenoble Alpes, France & Umm Al-Qura University, Saudi Arabia)
Ahmed Lbath (University of Grenoble Alpes, France) Abdullah Murad, Md. Abdur Rahman, Bilal
Sadiq, Saleh Basalamah (Umm Al-Qura University, Saudi Arabia) Akhlaq Ahmad (International
Islamic University Malaysia & Umm Al-Qura University, Saudi Arabia) Ahmad Qamar (University Sains
Malaysia & Umm Al-Qura University, Saudi Arabia)
Crowdsourced Multimedia Enhanced Spatio-temporal Constraint Based on-Demand Social
Network for Group Mobility
Bilal Sadiq, Md. Abdur Rahman, Abdullah Murad (Umm Al-Qura University, Saudi Arabia) Muhammad
Shahid (Ministry of Science and Technology, Pakistan) Faizan Ur Rehman (University of Grenoble
Alpes, France & Umm Al-Qura University, Saudi Arabia) Ahmed Lbath (University of Grenoble Alpes,
France) Akhlaq Ahmad (International Islamic University Malaysia & Umm Al-Qura University, Saudi
Arabia) Ahmad Qamar (University Sains Malaysia & Umm Al-Qura University, Saudi Arabia)
A Multi-sensory Gesture-Based Login Environment
Ahmad Qamar (University Sains Malaysia & Umm Al-Qura University, Saudi Arabia) Abdullah Murad,
Md. Abdur Rahman, Bilal Sadiq, Saleh Basalamah (Umm Al-Qura University, Saudi Arabia) Faizan
Ur Rehman (University of Grenoble Alpes, France & Umm Al-Qura University, Saudi Arabia) Akhlaq
Ahmad (International Islamic University Malaysia & Umm Al-Qura University, Saudi Arabia)
Hand-Object Sense: A Hand-held Object Recognition System Based on RGB-D Information
Xiong Lv, Shuqiang Jiang, Luis Herranz, Shuang Wang (Institute of Computing Technology, Chinese
Academy of Sciences)
ACM Multimedia 2015 Conference
39
Tuesday 27 October
Time:
11:00 – 17:30
Location:
P9
Session:
Video Session
Chair:
Alejandro Jaimes (Yahoo! Spain)
A Cross-media Sentiment Analytics Platform for Microblog
Chao Chen, Fuhai Chen, Donglin Cao, Rongrong Ji (Xiamen University, China)
A Unsupervised Person Re-identification Method Using Model Based Representation and
Ranking
Chao Liang, Binyue Huang, Ruimin Hu, Xiaoyuan Jing, Jing Xiao (Wuhan University, China) Chunjie
Zhang (University of Chinese Academy of Sciences)
Evolution of a Tabletop Telepresence System through Art and Technology
Tony Dunnigan, John Doherty, Daniel Avrahami, Jacob Biehl, Patrick Chiu, Chelhwon Kim, Qiong Liu,
Henry Tang, Lynn Wilcox (FX Palo Alto Laboratory, USA)
LiveTraj: Real-Time Trajectory Tracking over Live Video Streams
Tom Z. J. Fu, Zhenjie Zhang, Yong Pei, Bingbing Ni (Advanced Digital Sciences Center, Illinois at
Singapore Pte. Ltd.) Jianbing Ding (ADSC, Illinois at Singapore Pte. Ltd. & Sun Yat-sen University,
China) Richard T.B. Ma (National University of Singapore & ADSC, Illinois at Singapore Pte. Ltd.)
Marianne Winslett (ADSC, Illinois at Singapore Pte. Ltd. & University of Illinois at Urbana-Champaign,
USA) Yin Yang (Hamad Bin Khalifa University Qatar & ADSC, Illinois at Singapore Pte. Ltd.)
Automatic Accident Detection and Alarm System
Zhuo Wei, Tieyan Li (Shield Lab, Huawei International Pte. Ltd.) Swee-Won Lo, Jialie Shen, Robert H.
Deng (Singapore Management University) Yu Liang (Wuhan University, China)
Visible Light Communication via Temporal Psycho-Visual Modulation
Chunjia Hu, Guangtao Zhai, Zhongpai Gao (Shanghai Jiao Tong University, China)
Time:
12:30 – 14:30
Location:
P6
Session:
Women in SIGMM Lunch
Chair:
Klara Nahrstedt (University of Illinois at Urbana-Champaign, USA)
40
ACM Multimedia 2015 Conference
Tuesday 27 October
Time:
12:30 – 14:00
Location:
P7
Session:
Journal of Multimedia (JMM) Editorial Meeting
Chair:
Jiebo Luo (University of Rochester, USA)
Time:
12:30 – 14:30
Location:
P8
Session:
Multimedia Computing, Communications, and Applications (TOMM)
Editorial Meeting
Chair:
Ralf Steinmetz (University of Darmstadt, Germany)
Time:
14:00 – 15:30
Location:
Auditorium
Panel:
Opportunities and Challenges of Globally Networked Cameras
Chair:
Yung-Hsiang Lu (Purdue University, USA)
Panelists:
Joanna Batstone (IBM, Australia) Touradj Ebrahimi (EPFL, Switzerland)
Tiejun Huang (Peking University, China) Yonggang Wen (Nanyang
Technological University, Singapore)
Since the introduction of consumer digital cameras, user-created multimedia content has become
increasingly popular. Digital cameras, together with inexpensive editing tools, and free hosting sites
have made multimedia an integral part of everyday life. Today, hundreds of hours video are uploaded
to hosting sites every minute. Video-on-demand through wireless networks and smartphones have
profoundly changed how people consume multimedia content. Meanwhile, the widely deployed
network cameras can provide live views of many parts of the world. These cameras can provide
rich sources creating multimedia content. This panel will explore the opportunities and discuss the
challenges using global network cameras for creating multimedia contents and understanding the
world.
Every year, millions of network cameras are deployed. The data from some of these network cameras
are publicly available, continuously streaming live views of national parks, city halls, streets, highways,
and shopping malls. A person may see multiple tourist attractions through these cameras, without
leaving home. Researchers may observe the weather in different cities. Using the data from the
cameras, it is possible to observe natural disasters, such as volcano eruption or tsunami, at a safe
distance. News reporters may obtain instant views of an unfolding riot without risking their lives. A
spectator may watch a celebration parade from multiple locations using the street cameras. Despite
the many promising applications, the opportunities of using global network cameras for creating
multimedia content have not been fully exploited.
ACM Multimedia 2015 Conference
41
Tuesday 27 October
Time:
14:00 – 17:30
Location:
P6 – P11 Foyer
Session:
Short Paper Poster Session 1
Chair:
Jun Zhou (Griffith University, Australia)
Joint Modeling of Users’ Interests and Mobility Patterns for Point-of-Interest
Recommendation
Hongzhi Yin (The University of Queensland, Australia), Bin Cui (Peking University, China), Zi Huang,
Weiqing Wang (The University of Queensland, Australia), Xian Wu (Soochow University, China),
Xiaofang Zhou (The University of Queensland, Australia)
SHOE: Sibling Hashing with Output Embeddings
Sravanthi Bondugula, Varun Manjunatha, Larry S. Davis, David Doermann (University of Maryland
College Park, USA)
Supervised Hashing with Pseudo Labels for Scalable Multimedia Retrieval
Jingkuan Song (University of Trento, Italy), Lianli Gao (University of Electronic Science and Technology
of China), Yan Yan (University of Trento, Italy), Dongxiang Zhang (National University of Singapore),
Nicu Sebe (University of Trento, Italy)
Multi-view Latent Hashing for Efficient Multimedia Search
Xiaobo Shen (Nanjing University of Science and Technology, China), Fumin Shen, Quan-Sen Sun
(University of Electronic Science and Technology of China), Yun-Hao Yuan (Jiangnan University, China)
Jointly Estimating Interactions and Head, Body Pose of Interactors from Distant Social
Scenes
Ramanathan Subramanian, Jagannadan Varadarajan (Advanced Digital Sciences Center, Singapore),
Elisa Ricci, Oswald Lanz (Fondazione Bruno Kessler, Italy), Stefan Winkler (Advanced Digital Sciences
Center, Singapore)
Exploring Viewable Angle Information in Georeferenced Video Search
Gang Hu, Jie Shao, Lianli Gao, Yang Yang (University of Electronic Science and Technology of China)
Topic Hypergraph Hashing for Mobile Image Retrieval
Lei Zhu, Jialie Shen (Singapore Management University), Liang Xie (Wuhan University of Technology,
China)
Semi-supervised Coupled Dictionary Learning for Cross-modal Retrieval in Internet Images
and Texts
Xing Xu (Kyushu University, Japan), Yang Yang (University of Electronic Science and Technology of
China), Atsushi Shimada, Rin-ichiro Taniguchi (Kyushu University, Japan), Li He (Qualcomm Research
and Development Center, USA)
Vocabulary Expansion Using Word Vectors for Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda (Tokyo Institute of Technology, Japan)
42
ACM Multimedia 2015 Conference
Tuesday 27 October
Filter-Invariant Image Classification on Social Media Photos
Yu-Hsiu Chen, Ting-Hsuan Chao, Sheng-Yi Bai, Yen-Liang Lin, Wen-Chin Chen, Winston H. Hsu
(National Taiwan University)
Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios
Haiyun Guo, Jinqiao Wang (National Laboratory of Pattern Recognition, Institute of Automation,
Chinese Academy of Sciences), Min Xu (University of Technology, Sydney, Australia), Zheng-Jun Zha
(Institute of Intelligent Machines, Chinese Academy of Sciences), Hanqing Lu (National Laboratory of
Pattern Recognition, Institute of Automation,Chinese Academy of Sciences)
Unsupervised Extraction of Human-Interpretable Nonverbal Behavioral Cues in a Public
Speaking Scenario
M. Iftekhar Tanveer, Ji Liu, M. Ehsan Hoque (University of Rochester, USA)
Exploiting Word and Visual Word Co-occurrence for Sketch-based Clipart Image Retrieval
Ching-Hsuan Liu, Yen-Liang Lin, Wen-Feng Cheng, Winston H. Hsu (National Taiwan University)
Heterogeneous Graph-based Video Search Reranking using Web Knowledge via Social
Media Network
Soh Yoshida, Takahiro Ogawa, Miki Haseyama (Hokkaido University, Japan)
Selective K-means Tree Search
Tuan Anh Nguyen, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa (Graduate School of
Information Science and Technology, Japan)
Predicting Continuous Probability Distribution of Image Emotions in Valence-Arousal Space
Sicheng Zhao, Hongxun Yao, Xiaolei Jiang (Harbin Institute of Technology, China)
Towards Distributed Video Summarization
Shayok Chakraborty (Arizona State University, USA), Omesh Tickoo (Intel Labs, USA), Ravishankar
Iyer (Intel Labs, USA)
Semantic Image Search From Multiple Query Images
Gonzalo Vaca-Castano, Mubarak Shah (University of Central Florida, USA)
Geolocation with Subsampled Microblog Social Media
Miriam Cha (Harvard University, USA), Youngjune L Gwon (Harvard University & MIT Lincoln
Laboratory, USA), H. T. Kung (Harvard University, USA)
Social Tag Relevance Estimation via Ranking-Oriented Neighbour Voting
Chaoran Cui (Shandong University, China), Jialie Shen (Singapore Management University), Jun Ma,
Tao Lian (Shandong University, China)
EMV-matchmaker: Emotional Temporal Course Modeling and Matching for Automatic
Music Video Generation
Jen-Chun Lin (Academia Sinica, Taiwan), Wen-Li Wei (National Cheng Kung University, Taiwan), HsinMin Wang (Academia Sinica, Taiwan)
ACM Multimedia 2015 Conference
43
Tuesday 27 October
Scalable Multimedia Retrieval by Deep Learning Hashing with Relative Similarity Learning
Lianli Gao (University of Electronic Science and Technology of China), Jingkuan Song (University of
Trento, Italy), Fuhao Zou (Huazhong University of Science and Technology, China), Dongxiang Zhang
(National University of Singapore), Jie Shao (University of Electronic Science and Technology of China)
Image Popularity Prediction in Social Media Using Sentiment and Context Features
Francesco Gelli, Tiberio Uricchio, Marco Bertini, Alberto Del Bimbo (University of Florence, Italy), ShihFu Chang (Columbia University, USA)
Subtle Facial Expression Recognition Using Adaptive Magnification of Discriminative Facial
Motion
Sung Yeong Park, Seung Ho Lee, Yong Man Ro (KAIST, South Korea)
“Clustering of Dancelets” -- Towards Video Recommendation Based on Dance Styles
Tingting Han, Hongxun Yao, Xiaoshuai Sun, Yanhao Zhang, Sicheng Zhao, Xiusheng Lu, Yinghao
Huang, Wenlong Xie (Harbin Institute of Technology, China)
The Quest for Visual Interest
Mohammad Soleymani (University of Geneva, Switzerland)
How to Take a Good Selfie?
Mahdi M. Kalayeh (Center for Research in Computer Vision at University of Central Florida, USA),
Misrak Seifu (Jackson State University, USA), Wesna LaLanne (University of Central Florida, USA),
Mubarak Shah (Center for Research in Computer Vision at University of Central Florida, USA)
R2P: Recomposition and Retargeting of Photographic Images
Hui-Tang Chang, Po-Cheng Pan (National Taiwan University, Taiwan), Yu-Chiang Frank Wang
(Academia Sinica, Taiwan), Ming-Syan Chen (National Taiwan University, Taiwan)
Egocentric Video Summarization of Cultural Tour based on User Preferences
Patrizia Varini, Giuseppe Serra, Rita Cucchiara (University of Modena and Reggio Emlia, Italy)
A Novel Statistical Approach for Image and Video Retrieval and Its Adaption for Active
Learning
Moitreya Chatterjee, Anton Leuski (University of Southern California, USA)
Automatically Stereoscopic Camera Control for 3D Animation Production
Dawei Lu, Huadong Ma, Zeyu Wang, Liang Liu, Huiyuan Fu (Beijing University of Posts and
Telecommunications, China)
Color Photo Makeover via Crowd Sourcing and Recoloring
Wengang Cheng, Ruru Jiang (North China Electric Power University), Chang Wen Chen (State
University of New York at Buffalo, USA)
Multi-view Semi-supervised Learning for Web Image Annotation
Mengqiu Hu, Yang Yang (University of Electronic Science and Technology of China), Hanwang
Zhang (National University of Singapore), Fumin Shen, Jie Shao (University of Electronic Science and
Technology of China), Fuhao Zou (Huazhong University of Science and Technology, China)
44
ACM Multimedia 2015 Conference
Tuesday 27 October
Tracking Cultural Differences in News Video Creation
Chun-Yu Tsai, John R. Kender (Columbia University, USA)
Click-through-based Deep Visual-Semantic Embedding for Image Search
Yuan Liu, Zhongchao Shi (Ricoh Software Research Center (Beijing) Co., Ltd., China), Xue Li (Ricoh
Company, Ltd., Japan), Gang Wang (Ricoh Software Research Center (Beijing) Co., Ltd., China)
Partially Common-Semantic Pursuit for RGB-D Object Recognition
Lu Jin, Zechao Li, Xiangbo Shu (Nanjing University of Science and Technology, China), Shenghua
Gao (ShanghaiTech Universit, China), Jinhui Tang (Nanjing University of Science and Technology,
China)
Pinterest Board Recommendation for Twitter Users
Xitong Yang, Yuncheng Li, Jiebo Luo (University of Rochester, USA)
A Video Timeline with Bookmarks and Prefetch State for Faster Video Browsing
Axel Carlier, Vincent Charvillat (University of Toulouse, France), Wei Tsang Ooi (National University of
Singapore)
Giggler: An Intuitive, Real-Time Integrated Wireless In-Ear Monitoring and Personal Mixing
System using Mobile Devices
Andries Valstar, Min-Chieh Hsiu, Te-Yen Wu, Mike Y. Chen (National Taiwan University)
Dynamic Adjustment of Subtitles Using Audio Fingerprints
Lucas C. Villa Real, Rodrigo Laiola Guimarães, Priscilla Avegliano (IBM Research, Brazil)
Octave-dependent Probabilistic Latent Semantic Analysis to Chorus Detection of Popular
Song
Sheng Gao, Haizhou Li (Institute for Infocomm Research, A*STAR, Singapore)
Subjectivity in Aesthetic Quality Assessment of Digital Photographs: Analysis of User
Comments
Won-Hee Kim, Jun-Ho Choi, Jong-Seok Lee (Yonsei University, South Korea)
EEG Connectivity Analysis in Perception of Tone-mapped High Dynamic Range Videos
Seong-Eun Moon, Jong-Seok Lee (Yonsei University, South Korea)
Polyphonic Music Modelling with LSTM-RTRBM
Qi Lyu, Zhiyong Wu, Jun Zhu (Tsinghua University, China)
Multi-Sensor Cello Recordings for Instantaneous Frequency Estimation
Fabian-Robert Stöter (International Audio Laboratories Erlangen, Germany), Michael Müller (TU Graz,
Austria), Bernd Edler (International Audio Laboratories Erlangen, Germany)
An Elicitation Study on Gesture Attitudes and Preferences Towards an Interactive HandGesture Vocabulary
Haiwei Dong (University of Ottawa, Canada), Nadia Figueroa (Swiss Federal Institute of Technology
Lausanne, Switzerland), Abdulmotaleb El Saddik (University of Ottawa, Canada)
ACM Multimedia 2015 Conference
45
Tuesday 27 October
Automated Video Editing for Aesthetic Quality Improvement
Jun-Ho Choi, Jong-Seok Lee (Yonsei University, South Korea)
Multimodal Dataset for Assessment of Quality of Experience in Immersive Multimedia
Anne-Flore Nicole Marie Perrin, He Xu, Eleni Kroupi, Martin Rerabek, Tourajd Ebrahimi (MMSPG,
EPFL, Switzerland)
MIL: Music Exploration and Visualization via Lyric and Image
Xixuan Wu (The Chinese University of Hong Kong), Yu Qiao (Shenzhen Institutes of Advanced
Technology, Chinese Academy of Sciences), Xiaoou Tang (The Chinese University of Hong Kong)
ESC: Dataset for Environmental Sound Classification
Karol J. Piczak (Warsaw University of Technology, Poland)
Improving Feature Aggregation for Semantic Music Retrieval
Zhouyu Fu (University of Western Sydney, Australia)
Accelerating Large-scale Image Retrieval on Heterogeneous Architectures with Spark
Hanli Wang, Bo Xiao, Lei Wang, Jun Wu (Tongji University, China)
Implementation of Face Recognition for Screen Unlockingon Mobile Device
Chung-Hua Chu, Shih-Ming Peng (National Taichung University of Science and Technology, Taiwan)
Web-based Interactive Free-Viewpoint Streaming
Matthias Ueberheide, Felix Klose (TU Braunschweig, Germany), Tilak Varisetty, Markus Fidler (Leibniz
Universitaet Hannover, Germany), Marcus Magnor (TU Braunschweig, Germany)
Distributed Bandwidth-efficient Packet Scheduling for Live Streaming with Network Coding
Shenglan Huang, Ebroul Izquierdo, Pengwei Hao (Queen Mary, University of London, UK)
Vision-Inertial Hybrid Tracking for Robust and Efficient Augmented Reality on Smartphones
Xin Yang, Xun Si (Huazhong University of Science and Technology, China), Tangli Xue, Liheng Zhang
(School of Electronics Information and Communications, China), Kwang-Ting (Tim) Cheng (University
of California, Santa Barbara, USA)
An SDN Controller for Delay and Jitter Reduction in Cloud Gaming
Maryam Amiri, Hussein Al Osman, Shervin Shirmohammadi (University of Ottawa, Canada), Maha
Abdallah (Pierre and Marie Curie University, France)
The invisible QR code
Zhongpai Gao, Guangtao Zhai, Chunjia Hu (Institute of Image Communication and Information
Processing, Shanghai Jiao Tong University, China)
3D Background Modeling in Multi-view RGB-D Video
Yung-Lin Huang, Ku-Chu Wei, Shao-Yi Chien (National Taiwan University)
Audio Routing for Scalable Conferencing using AAC-ELD and Bit Stream Domain Energy
Estimation
Iaroslav Kryvyi, Nikolaus Färber, Conrad Benndorf, Manfred Lutzky (Fraunhofer IIS, Germany)
46
ACM Multimedia 2015 Conference
Tuesday 27 October
EcoFlow: An Economical and Deadline-Driven Inter-Datacenter Video Flow Scheduling
System
Yuhua Lin, Haiying Shen, Liuhua Chen (Clemson University, USA)
Ciphertext-Only Attack on an Image Homomorphic Encryption Scheme with Small
Ciphertext Expansion
Yunyu Li, Jiantao Zhou, Yuanman Li (Faculty of Science and Technology, University of Macau)
Time:
14:00 – 15:30
Location:
P7
Oral Session 1:
Multimedia Indexing and Search
Chair:
Heng Tao Shen (The University of Queensland, Australia)
Fast and Accurate Content-based Semantic Search in 100M Internet Videos
Lu Jiang, Shoou-I Yu (Carnegie Mellon University, USA), Deyu Meng (Xi’an Jiaotong University, China),
Yi Yang (University of Technology Sydney, Australia), Teruko Mitamura, Alexander G Hauptmann
(Carnegie Mellon University, USA)
Visual Coding in a Semantic Hierarchy
Yang Yang (University of Electronic Science and Technology of China), Hanwang Zhang (National
University of Singapore), Mingxing Zhang, Fumin Shen (University of Electronic Science and
Technology of China), Xuelong Li (Chinese Academy of Sciences)
Deep Compositional Cross-modal Learning to Rank via Local-Global Alignment
Xinyang Jiang, Fei Wu, Xi Li, Zhou Zhao, Weiming Lu, Siliang Tang, Yueting Zhuang (Zhejiang
University, China)
Effective Multi-Query Expansions: Robust Landmark Retrieval
Yang Wang, Xuemin Lin (The University of New South Wales, Australia), Lin Wu (The University of
Adelaide, Australia), Wenjie Zhang (The University of New South Wales, Australia)
ACM Multimedia 2015 Conference
47
Tuesday 27 October
Time:
16:00 – 18:00
Location:
Auditorium
Session:
Open Source Software Competition
Chairs:
Tao Mei (Microsoft Research Asia, China) Marco Bertini (University of
Florence, Italy) Xian-Sheng Hua (Alibaba, China)
Theia: A Fast and Scalable Structure-from-Motion Library
Chris Sweeney, Tobias Hollerer, Matthew Turk (UC Santa Barbara, USA)
SINGA: A Distributed Deep Learning Platform
Beng Chin Ooi, Kian-Lee Tan, Sheng Wang, Wei Wang, Qingchao Cai, Jinyang Gao, Zhaojing Luo,
Zhongle Xie, Kaiping Zheng (National University of Singapore) Gang Chen (Zhejiang University, China)
Yuan Wang (NetEase, Singapore)
MatConvNet
Andrea Vedaldi, Karel Lenc (University of Oxford, UK)
The fertilized forests Decision Forest library
Christoph Lassner (University of Augsburg, Germany)
Amalia.js: an open-source metadata driven HTML5 multimedia player
Nicolas Hervé, Pierre Letessier, Mathieu Derval, Hakim Nabi (INA, France)
SIVA Suite: Framework for Hypervideo Creation, Playback and Management
Britta Meixner, Stefan John, Christian Handschigl (University of Passau, Germany)
Aurio: Audio Processing, Analysis and Retrieval
Mario Guggenberger (University of Klagenfurt, Austria)
eRS – A system to facilitate emotion recognition in movies
Joël Dumoulin, Diana Affi, Elena Mugellini, Omar Abou Khaled (HumanTech Institute
(HES-SO), Switzerland)
WATTS: a Web Annotation Tool for Surveillance Scenarios
Federico Bartoli, Lorenzo Seidenari, Giuseppe Lisanti, Alberto Del Bimbo (University of Florence, Italy)
Svebor Karaman (Columbia University, USA)
48
ACM Multimedia 2015 Conference
Tuesday 27 October
Time:
16:00 – 17:30
Location:
P7
Oral Session 2:
Social Multimedia
Chair:
Tao Mei (Microsoft Research Asia, China)
What are Popular: Exploring Twitter Features for Event Detection, Tracking and
Visualization
Hongyun Cai (The University of Queensland, Australia), Yang Yang (University of Electronic Science
and Technology of China), Xuefei Li, Zi Huang (The University of Queensland, Australia)
Cross-Domain Collaborative Learning in Social Multimedia
Shengsheng Qian, Tianzhu Zhang (National Lab of Pattern Recognition, Institute of Automation, CAS,
China), Richang Hong (School of Computer and Information, Hefei University of Technology, China),
Changsheng Xu (National Lab of Pattern Recognition, Institute of Automation, CAS, China)
Learning Socially Embedded Visual Representation from Scratch
Shaowei Liu, Peng Cui, Wenwu Zhu, Shiqiang Yang (Tsinghua University, China)
Spatial-aware Multimodal Location Estimation for Social Images
Jiewei Cao, Zi Huang (The University of Queensland, Australia), Yang Yang (University of Electronic
Science and Technology of China)
Time:
16:00 – 17:30
Location:
P8
Oral Session 3:
Emotional and Social Signals in Multimedia
Chair:
Hayley Hung (Technical University of Delft, The Netherlands)
Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach
Yang Hu, Xi Yi, Larry S. Davis (University of Maryland, USA)
Predicting and Understanding Urban Perception with Convolutional Neural Networks
Lorenzo Porzi, Samuel Rota Bulò, Bruno Lepri, Elisa Ricci (Fondazione Bruno Kessler, University of
Perugia, Italy)
A Multimodal Predictive Model of Successful Debaters or How I Learned to Sway Votes
Maarten Brilman (University of Twente, The Netherlands), Stefan Scherer (USC Institute for Creative
Technologies, USA)
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology
Brendan Jou, Tao Chen (Columbia University, USA), Nikolaos Pappas (Idiap Research Institute,
Switzerland), Miriam Redi (Yahoo Labs, United Kingdom), Mercan Topkara (JW Player, USA), Shih-Fu
Chang (Columbia University, USA)
ACM Multimedia 2015 Conference
49
Tuesday 27 October
Time:
18:00 – 20:00
Location:
P10 – P11 and Foyer
Session:
Art Exhibit Opening and Welcome Reception
Using Handmade Controllers for Interactive Projection Mapping
Alinta K. Krauth (Griffith University, Australia)
3D Printing and Camera Mapping: Dialectic of Virtual and Reality
He-Lin Luo, Yi-Ping Hung (National Taiwan University) I-Chun Chen (Taipei National University of the
Arts, Taiwan)
Drag A Star – the Social Media in Outer Space
James She (Hong Kong University of Science & Technology) Cameron Ng (JM Network, Hong Kong)
Desmond Leung (Desmond Leung Media Arts, Hong Kong)
Disturbed System: Recreating Sculptor’s Experience of Their Medium With Haptics and
Generated Sound
Oksana Krzyhanivska, Simon Fay, Jeffrey E. Boyd (University of Calgary, Canada)
The Real Time Rolling Shutter
David S. Monaghan, Noel E. O’Connor (Dublin City University, Ireland) Anne Cleary, Denis Connolly
(Independent artists, France)
50
ACM Multimedia 2015 Conference
Wednesday 28 October
Conference Day 2
Time:
9:00 – 10:30
Location:
Auditorium
Session:
SIGMM Awards and Plenary Talks
Chair:
Shih-Fu Chang (SIGMM Chair)
Multimedia Retrieval: Reviewing the Past and Present, Previewing the Future
Dr. Tat-Seng Chua (National University of Singapore)
SIGMM Award for Outstanding Technical Contributions to Multimedia Computing, Communications
and Applications
Multimedia has long been associated with visual media by many researchers. While visual media is
one of the most challenging medium to deal with, the use of visual analysis alone is neither sufficient
nor necessary to tackle many real-life problems. The current wisdom seems to suggest that for
real-world problem solving, it is necessary to make fuller use of content information including text
and audio, and various kinds of contextual information, such as the user’s mobile device settings,
social postings, check-in history etc., when available. This talk presents a personal journey in
multimedia retrieval research. It reviews early research in 1990, where researchers mainly focused
on mono-media research; to the seminal SIGMM strategic retreat in 2003, where one of the key
recommendations was for multimedia research to “incorporate correlated media, fuse data from
different sources, and use context to improve application performance”; and to present day setting,
where social media, videos, various kinds of sensors and big data are making big impact on people’s
life. It is obvious that multimedia research should model and tackle these problems. This talk further
discusses current problems, suggests directions to move forward as a research community, and
outlines approaches to make our community more inclusive.
Video Content Recognition with Deep Learning
Dr. Yu-Gang Jiang (Fudan University, China)
ACM SIGMM Rising Star Award
Nowadays people produce a huge number of videos and many of them are uploaded to the Internet.
There is a strong need to develop automatic solutions for recognizing the contents of these videos.
Potential applications of such techniques include effective video content management and retrieval,
open-source intelligence analysis, etc. In this talk, I will introduce our recent works on video content
analysis. I will start by introducing a few recently constructed Internet video datasets. After that I will
introduce several deep learning based approaches recently developed in my group.
ACM Multimedia 2015 Conference
51
Wednesday 28 October
Bridging Vision and Text for Multimedia Search
Dr. Ting Yao (City University of Hong Kong) (Microsoft Research)
SIGMM Outstanding Ph.D. Thesis Award
Over decades, harvesting right data for right problem has been a grand challenge in multimedia
field. The fundamental issue is, without the right and sensible way of leveraging data, mixing data of
different natures can always result in uncertain performance. In this talk, we present our research on
how to bridge vision and text, in the context of multimedia search. We study this problem from the
viewpoint of cross-view embedding, that is, integrate content, structure, and/or click data for learning
a joint space that connects different natures of vision and text. We demonstrate the success of our
technologies in a wide range of applications such as image object recognition, image search, video
concept detection, video tagging, and video-to-sentence, and then share views about promising
future directions.
Time:
11:00 – 12:30
Location:
Auditorium
Session:
Grand Challenge Presentations
Chair:
David A Shamma (Yahoo! Labs, USA)
Microsoft Grand Challenge
Image Retrieval by Cross-Media Relevance Fusion
Xirong Li (Renmin University of China) Jianfeng Dong (Zhejiang University) Xirong Li, Shuai Liao,
Jieping Xu (Renmin University of China)
Learning Deep Features For MSR-bing Information Retrieval Challenge
Song Qiang, Sixie Yu, Cong Leng, Jiaxiang Wu, Qinghao Hu, Jian Cheng (Chinese Academy of
Sciences)
IBM Grand Challenge
What Makes New York So Noisy? Reasoning Urban Noise Pollution from Multimodal
Geo-Social Media Data
Cheng-Te Li (Academia Sinica, Taiwan) Hsun-Ping Hsieh (National Taiwan University) Tzu-Chi Yen
(Sensoro Technology Co. Ltd., China)
Who are the devils wearing Parada in New York City?
KuanTing Chen, Kezhen Chen, Peizhong Cong, Jiebo Luo (University of Rochester, USA)
52
ACM Multimedia 2015 Conference
Wednesday 28 October
Yahoo! Grand Challenge
EventBuilder: Real-time Multimedia Event Summarization by Visualizing Social Media
Rajiv Ratn Shah (National University of Singapore) Anwar Dilawar Shaikh (Delhi Technological
University, India) Yi Yu (National Institute of Informatics, Japan) Wenjing Geng (Nanjing University,
China) Roger Zimmermann (National University of Singapore) Gangshan Wu (Nanjing University,
China)
Multimodal Graph-based Event Detection and Summarization in Social Media Streams
Manos Schinas, Symeon Papadopoulos (Certh ITI, Greece)
Evento 360: Social Event Discovery from Web-scale Multimedia Collection
Jaeyoung Choi, Eungchan Kim (International Computer Science Institute, USA / Delft University of
Technology, The Netherlands) Martha Larson (Delft University of Technology, The Netherlands) Gerald
Friedland (International Computer Science Institute, USA) Alan Hanjalic (Delft University of Technology,
The Netherlands)
Unsupervised Latent Aspect Discovery for Diverse Event Summarization
Wen-Yu Lee, Yin-Hsi Kuo, Peng-Ju Hsieh, Wen-Feng Cheng, Ting-hsuan Chao, Hui-lan Hsieh,
Chieh-En Tsai, Hsiao-Ching Chang, Jia-Shin Lan, Winston Hsu (National Taiwan University)
Time:
11:00 – 17:30
Location:
P9
Session:
Demo Session 2
Chair:
Zheng-Jun Zha (Hefei Institute of Intelligent Machines, Chinese Academy
of Sciences)
What Shall I Look Like after N Years?
Xiangbo Shu, Jinhui Tang (Nanjing University of Science and Technology, China) Luoqi Liu, Zhiheng
Niu, Shuicheng Yan (National University of Singapore)
Searching and Browsing Live, Web-based Meetings
Scott Carter, Laurent Denoue, Matthew Cooper (FX Palo Alto Laboratory, Inc., USA)
Deep Face Beautification
Jianshu Li, Luoqi Liu, Shuicheng Yan (National University of Singapore) Chao Xiong (Imperial College,
UK) Xiangbo Shu (Nanjing University of Science and Technology, China)
Pan360: INS Assisted 360-Degree Panorama (Demo Description)
Yu-Hsin Lin, Yu-Mei Chen, Lun-Cheng Chu, Andre Chen, Scott Chien-Hung Liao, Edward Y. Chang
(HTC Research, Taiwan)
ACM Multimedia 2015 Conference
53
Wednesday 28 October
HeartHealth: New Adventures in Serious Gaming
David S. Monaghan, Freddie Honohan, Edmond Mitchell, Noel E. O’Connor (Dublin City University,
Ireland) Anargyros Chatzitofis, Dimitrios Zarpalas, Petros Daras (Information Technologies Institute/
Centre for Research and Technology Hellas, Greece)
Challenged Content Delivery Network: Eliminating the Digital Divide
Hua-Jun Hong, Shu-Ting Wang, Chih-Pin Tan, Cheng-Hsin Hsu (National Tsing Hua University,
Taiwan) Tarek El-Ganainy, Mohamed Hefeeda (Qatar Computing Research Institute, HBKU) Khaled
Harras (Carnegie Mellon University, USA)
OmniViewer: Enabling Multi-modal 3D DASH
Zhenhuan Gao, Shannon Chen, Klara Nahrstedt (University of Illinois at Urbana-Champaign, USA)
Large Video Event Ontology Browsing, Search and Tagging (EventNet Demo)
Hongliang Xu, Guangnan Ye, Yitong Li, Dong Liu, Shih-Fu Chang (Columbia University, USA)
MASTER: Multi-platform Application Streaming Toolkits for Elastic Resources
Yusen Li, Yunhua Deng, Ronald Seet, Xueyan Tang, Wentong Cai (Nanyang Technological University,
Singapore)
smArt: Open and Interactive Indoor Cultural Data
Andrea Ferracani, Daniele Pezzatini, Alberto Del Bimbo, Riccardo Del Chiaro, Franco Yang, Maurizio
Sanesi (Università degli Studi di Firenze – MICC, Italy)
i-Diary: A Crowdsource-based Spatio-Temporal Multimedia Enhanced Points of Interest
Authoring Tool
Akhlaq Ahmad (International Islamic University Malaysia & Umm Al Qura University, Saudi Arabia)
Faizan ur Rehman (Umm Al Qura University, Saudi Arabia & University of Grenoble Alpes, France)
Md. Abdur Rahman, Abdullah Murad, Bilal Sadiq, Salah Basalamah (Umm Al Qura University, Saudi
Arabia) Ahmad Qamar (University Sains Malaysia & Umm Al Qura University, Saudi Arabia) Mohamed
Ridza Wahiddin (International Islamic University Malaysia)
B-box Mixer: An Interactive UI for Generating B-box Music
Yi-Zhu Dai, Ting-Chia Lee, Xin-Yu Kuo, Tse-Yu Pan, Min-Chun Hu (National Cheng Kung University,
Taiwan)
DeepFont: A System for Font Recognition and Similarity
Zhangyang Wang, Thomas Huang (University of Illinois at Urbana-Champaign, USA) Jianchao Yang
(Snapchat, USA) Hailin Jin, Jonathan Brandt, Eli Shechtman, Zhaowen Wang, Yuyan Song, Joseph
Hsieh, Sarah Kong (Adobe, USA) Aseem Agarwala (Google, USA)
ObjectMinutiae: Fingerprinting for Object Authentication
Tzu-Yun Lin, Yu-Chiang Frank Wang (Research Center for IT Innovation, Academia Sinica, Taiwan)
Sean Moss-Pultz (Bitmark, Inc., Taiwan)
Hyper Video Browser: Search and Hyperlinking in Broadcast Media
Maria Eskevich, Huynh Nguyen, Mathilde Sahuguet, Benoit Huet (EURECOM, France)
54
ACM Multimedia 2015 Conference
Wednesday 28 October
Time:
11:00 – 17:30
Location:
P10–11
Session:
Art Exhibit
Time:
12:30 – 14:30
Location:
P6
Session:
IEEE Multimedia Magazine Editorial Meeting
Chair:
Alan Hanjalic (University of Delft, The Netherlands)
Time:
12:30 – 14:30
Location:
P7
Session:
Multimedia Systems Journal (MMSJ) Editorial Meeting
Chair:
Thomas Plagemann (University of Oslo, Norway)
Time:
12:30 – 15:30
Location:
P8
Session:
Doctoral Symposium
Chairs:
Hervé Jégou (Facebook AI Research, France) Cees G. M. Snoek (University
of Amsterdam, The Netherlands)
Real-Time Assistance in Multimedia Capture Using Social Media
Yogesh Singh Rawat (National University of Singapore)
Intuitive Input Methods for Interactive Segmentation on Mobile Touch-Based Devices
Christoph Korinke (OFFIS – Institute for Information Technology, Germany)
Exploiting Contextual Information to Enable Efficient Content Delivery for 3D TeleImmersion Applications
Shannon Chen (University of Illinois at Urbana-Champaign, USA)
Socializing Multimodal Sensors for Information Fusion
Yuhui Wang (National University of Singapore)
Learn to Recognize Actions Through Neural Networks
Zhenzhong Lan (Carnegie Mellon University, USA)
ACM Multimedia 2015 Conference
55
Wednesday 28 October
Challenge for Manga Processing: Sketch-based Manga Retrieval
Yusuke Matsui (The University of Tokyo, Japan)
Captioning Images Using Different Styles
Alexander Mathews (Australian National University)
Weakly Supervised Learning of Part-based Models for Interaction Prediction via LDA
Jia-Lin Chen (National Taiwan University)
Time:
14:00 – 15:30
Location:
Auditorium
Session:
Brave New Ideas
Chair:
Nicu Sebe (University of Trento, Italy)
How Was It? Exploiting Smartphone Sensing to Measure Implicit Audience Responses to
Live Performances
Claudio Martella (VU University of Amsterdam, The Netherlands) Ekin Gedik, Laura Cabrera-Quiros,
Hayley Hung (Delft University of Technology, The Netherlands) Gwenn Englebienne (University of
Twente, The Netherlands)
Loud and Trendy: Crowdsourcing Impressions of Social Ambiance in Popular Indoor Urban
Places
Darshan Santani, Daniel Gatica-Perez (Idiap Research Institute and EPFL, Switzerland)
Bringing Deep Causality to Multimedia Data Streams
Laleh Jalali, Ramesh Jain (University of California, Irvine, USA)
Analytic Quality: Evaluation of Performance and Insight in Multimedia Collection Analysis
Jan Zahálka, Stevan Rudinac, Marcel Worring (University of Amsterdam, The Netherlands)
Time:
14:00 – 17:30
Location:
P6 – P11 Foyer
Session:
Short Paper Poster Session 2
Chair:
Dian Tjondronegoro (Queensland University of Technology, Australia)
Sense Beyond Expressions: Cuteness
Kang Wang (Rensselaer Polytechnic Institute, USA), Tam V Nguyen (Singapore Polytechnic), Jiashi
Feng (University of California, Berkeley, USA), Jose Sepulveda (Singapore Polytechnic)
56
ACM Multimedia 2015 Conference
Wednesday 28 October
Joint Visual-Textual Sentiment Analysis with Deep Neural Networks
Quanzeng You, Jiebo Luo (University of Rochester, USA), Hailin Jin (Adobe Research, USA), Jianchao
Yang (Snapchat Inc, USA)
Attribute Mining for Scalable 3D Human Action Recognition
Xingyang Cai, Wengang Zhou, Houqiang Li (Dept. of EEIS, University of Science and Technology of
China)
Learning Features from Large-Scale, Noisy and Social Image-Tag Collection
Hanwang Zhang, Xindi Shang (National University of Singapore), Huanbo Luan (Tsinghua University,
China), Yang Yang (University of Electronic Science and Technology of China),
Tat-Seng Chua (National University of Singapore)
Saliency Detection Based on Graph-Structural Agglomerative Clustering
Youbao Tang, Xiangqian Wu, Wei Bu (Harbin Institute of Technology, China)
Detecting Salient Objects via Spatial and Appearance Compactness Hypotheses
Ping Hu, Weiqiang Wang, Ke Lu (University of Chinese Academy of Sciences)
A Probabilistic Approach for Image Retrieval Using Descriptive Textual Queries
Yashaswi Verma, C. V. Jawahar (IIIT Hyderabad (India))
Multi-cue Augmented Face Clustering
Chengju Zhou (Institute of Information Engineering, Chinese Academy of Sciences), Changqing Zhang
(Tianjin Universtiy, China), Huazhu Fu (Nanyang Technological University, Singapore), Rui Wang,
Xiaochun Cao (Institute of Information Engineering, Chinese Academy of Sciences)
Robust Deep Auto-encoder for Occluded Face Recognition
Lele Cheng, Jinjun Wang, Yihong Gong, Qiqi Hou (Institute of Artificial Intelligence and Robotics, Xi’an
Jiaotong University, China)
Dissecting Urban Noises from Heterogeneous Geo-Social Media and Sensor Data
Hsun-Ping Hsieh (National Taiwan University), Rui Yan (Baidu Inc., Taiwan), Cheng-Te Li (Academia
Sinica, Taiwan)
Deep Multimodal Speaker Naming
Yongtao Hu (The University of Hong Kong, China), Jimmy SJ. Ren (SenseTime Group Limited, China),
Jingwen Dai (Xim Industry Inc., China), Chang Yuan (Lenovo Group Limited, China), Li Xu (SenseTime
Group Limited, China), Wenping Wang (The University of Hong Kong, China)
Cross-Modal Image-Tag Relevance Learning for Social Images
Yong Cheng, Zhengxiang Cai, Rui Feng, Cheng Jin, Yuejie Zhang (Fudan University, China), Tao
Zhang (Shanghai University of Finance and Economics, China)
Local Depth Patterns for Tracking in Depth Videos
Sari Awwad, Fairouz Hussein, Massimo Piccardi (University of Technology Sydney, Australia)
ACM Multimedia 2015 Conference
57
Wednesday 28 October
ConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and
Pseudocoloring
Pichao Wang, Wanqing Li, Zhimin Gao, Chang Tang, Jing Zhang, Philip Ogunbona (Advanced
Multimedia Research Lab, University of Wollongong, Australia)
Spatio-Temporal Learning of Basketball Offensive Strategies
Ching-Hang Chen, Tyng-Luh Liu (Institute of Information Science, Academia Sinica, Taiwan), YuShuen Wang (National Chiao Tung University, Taiwan), Hung-Kuo Chu (National Tsing Hua University,
Taiwan), Nick C. Tang, Hong-Yuan Mark Liao (Institute of Information Science, Academia Sinica,
Taiwan)
Weak Labeled Multi-Label Active Learning for Image Classification
Shiquan Zhao, Jian Wu (Soochow University, China), Victor S. Sheng (University of Central Arkansas,
USA), Chen Ye, Pengpeng Zhao, Zhiming Cui (Soochow University, China)
Probabilistic Semi-Canonical Correlation Analysis
Chie Kamada, Asako Kanezaki, Tatsuya Harada (The University of Tokyo, Japan)
Recognizing Human Activity in Still Images by Integrating Group-Based Contextual Cues
Zheng Zhou, Kan LI (Beijing Institute of Technology, China), Xiangjian He (University of Technology,
Sydney, Australia)
3D Person Tracking In World Coordinates and Attribute Estimation with PDR
Yuki Nagai, Daisuke Kamisaka, Naoya Makibuchi, Jianfeng Xu, Shigeyuki Sakazawa (KDDI R&D
Laboratories, Inc., Japan)
Image Tagging via Cross-Modal Semantic Mapping
Zhi-Hong Deng, Hongliang Yu, Yunlun Yang (Peking University, China)
Predicting Image Memorability by Multi-view Adaptive Regression
Houwen Peng (Chinese Academy of Sciences & Temple University, USA), Kai Li, Bing Li (Chinese
Academy of Sciences), Haibin Ling (Temple University, USA), Weihua Xiong, Weiming Hu (Chinese
Academy of Sciences)
Spatio-Temporal Triangular-Chain CRF for Activity Recognition
Congqi Cao, Yifan Zhang, Hanqing Lu (National Laboratory of Pattern Recognition, Institute of
Automation, Chinese Academy of Sciences)
Query-Adaptive Logo Search using Shape-Aware Descriptors
Sreyasee Das Bhattacharjee, Yuan Junsong, Yap-Peng Tan (Nanyang Technological University,
Singapore), Lingyu Duan (Peking University, China)
Hyperspectral Image Classification with Convolutional Neural Networks
Viktor Slavkovikj, Steven Verstockt, Wesley De Neve, Sofie Van Hoecke, Rik Van de Walle (Ghent
University-iMinds, Belgium)
Online Object Tracking Based on CNN with Metropolis-Hasting Re-Sampling
Xiangzeng Zhou, Lei Xie, Peng Zhang, Yanning Zhang (Northwestern Polythechnical University, China)
58
ACM Multimedia 2015 Conference
Wednesday 28 October
Progressive Shape-Distribution-Encoder for 3D Shape Retrieval
Jin Xie, Fan Zhu (New York University Abu Dhabi, UAE), Guoxian Dai (New York University, USA), Yi
Fang (New York University Abu Dhabi, UAE)
Cross-media Topic Detection with Refined CNN based Image-Dominant Topic Model
Zhiyi Wang, Liang Li, Qingming Huang (University of Chinese Academy of Sciences)
Human Action Recognition With Trajectory Based Covariance Descriptor In Unconstrained
Videos
Hanli Wang, Yun Yi, Jun Wu (Tongji University, China)
RECfusion: Automatic Video Curation Driven by Visual Content Popularity
Alessandro Ortis, Giovanni Maria Farinella (University of Catania, Italy), Valeria D’amico, Luca
Addesso, Giovanni Torrisi (Telecom Italia – JOL WAVE, Italy), Sebastiano Battiato (University of
Catania, Italy)
Gender Classification Using Pyramid Segmentation for Unconstrained Back-facing Video
Sequences
Hao Tang, Hong Liu, Wei Xiao (Shenzhen Graduate School, Peking University, China)
Object Segmentation from Long Video Sequences
Bing Luo, Hongliang Li, Tiecheng Song, Chao Huang (University of Electronic Science and
Technology of China)
Summarization-based Video Caption via Deep Neural Networks
Guang Li, Shubo Ma, Yahong Han (Tianjin University, China)
Multi-modal & Multi-view & Interactive Benchmark Dataset for Human Action Recognition
Ning Xu, Anan Liu, Weizhi Nie (Tianjin University, China), Yongkang Wong (National University of
Singapore), Fuwu Li, Yuting Su (Tianjin University, China)
A Deep Siamese Network for Scene Detection in Broadcast Videos
Lorenzo Baraldi, Costantino Grana, Rita Cucchiara (University of Modena and Reggio Emilia, Italy)
Unsupervised Cosegmentation based on Global Graph Matching
Takanori Tamanaha, Hideki Nakamaya (Grad. School of IST, The University of Tokyo, Japan)
Facial Age Estimation Based on Structured Low-rank Representation
Chenjing Yan, Congyan Lang, Songhe Feng (Beijing Jiaotong University, China)
Semantic Segmentation based on Stacked Discriminative Autoencoders and ContextConstrained Weakly Supervised Learning
Xiwen Yao, Junwei Han, Gong Cheng, Lei Guo (Northwestern Polytechnical University, China)
Deep Self-taught Hashing for Image Retrieval
Ke Zhou, Yu Liu (Huazhong University of Science and Technology, China), Jingkuan Song (University
of Trento, Italy), Linyu Yan (Hubei University of Technology, China), Fuhao Zou (Huazhong University
of Science and Technology, China), Fumin Shen (University of Electronic Science and Technology of
China)
ACM Multimedia 2015 Conference
59
Wednesday 28 October
GPU Accelerated Generalised Subclass Discriminant Analysis for Event and Concept
Detection in Video
Stavros Arestis-Chartampilas, Nikolaos Gkalelis, Vasileios Mezaris (CERTH-ITI, Greece)
Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural
Networks
Yuhang Wang, Jing Liu, Yong Li, Hanqing Lu (Institute of Automation, Chinese Academy of Sciences)
Learning Pairwise Neural Network Encoder for Depth Image-based 3D Model Retrieval
Jing Zhu (New York University, USA), Fan Zhu (New York University Abu Dhabi, UAE), Edward K Wong
(New York University, USA), Yi Fang (New York University Abu Dhabi, UAE)
Using the Eyes to “See” the Objects
Concetto Spampinato, Simone Palazzo, Francesca Murabito, Daniela Giordano (University of Catania,
Italy)
Discriminative Light Unsupervised Learning Network for Image Representation and
Classification
Le Dong, Ling He (Univ. of Electronic Science and Technology of China), Qianni Zhang (Queen Mary
Univ. of London, UK)
Ranking Optimization for Person Re-identification via Similarity and Dissimilarity
Mang Ye, Chao Liang, Zheng Wang (Wuhan Univeristy, China), Qingming Leng (Jiujiang University,
China), Jun Chen (Wuhan University, China)
Leveraging Knowledge-based Inference for Material Classification
Jie Yu, Sandra Skaff, Liang Peng, Francisco Imai (Canon Innovation Center, USA)
Emotion Distribution Recognition from Facial Expressions
Ying Zhou, Hui Xue, Xin Geng (Southeast University, China)
Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic
Segmentation
Peng Ying, Jin Liu, Hanqing Lu, Songde Ma (Institute of Automation, Chinese Academy of Sciences)
Multimedia Event Detection Using Event-Driven Multiple Instance Learning
Sang Phan, Duy-Dinh Le, Shin’ichi Satoh (National Institute of Informatics, Japan)
Learning Semantic Correlation of Web Images and Text with Mixture of Local Linear
Mappings
Youtian Du, Kai Yang (Xi’an Jiaotong University, China)
Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition
Grigory Antipov, Sid-Ahmed Berrani (Orange Labs, France), Natacha Ruchaud, Jean-Luc Dugelay
(Eurecom, France)
60
ACM Multimedia 2015 Conference
Wednesday 28 October
Multi-Level Fusion for Person Re-identification with Incomplete Marks
Zheng Wang, Ruimin Hu (National Engineering Research Center for Multimedia Software, Computer
School of Wuhan Univ., China), Yi Yu (National Institute of Informatics, Japan), Chao Liang, Wenxin
Huang (National Engineering Research Center for Multimedia Software, Computer School of Wuhan
Univ., China)
Offloading Guidelines for Augmented Reality Applications on Wearable Devices
Bowen Shi, Ji Yang, Zhanpeng Huang, Pan Hui (The Hong Kong University of Science and
Technology)
Real-Time Instant Event Detection in Egocentric Videos by Leveraging Sensor-Based
Motion Context
Pei-Yun Hsu, Wen-Feng Cheng, Peng-Ju Hsieh, Yen-Liang Lin, Winston H. Hsu (National Taiwan
University)
Modeling Temporal Effects in Re-captured Video
Philipp Schaber, Sally Dong, Benjamin Guthier, Stephan Kopf, Wolfgang Effelsberg (University of
Mannheim, Germany)
On the Benefit of Synthetic Data for Company Logo Detection
Christian Eggert, Anton Winschel, Rainer Lienhart (University of Augsburg, Germany)
Retrieving Unfamiliar Faces: Towards Understanding Human Performance
Xu Zhou, Baoxin Li (Arizona State University, USA)
Acoustic Scene Classification based on Sound Textures and Events
Jiaxing Ye, Takumi Kobayashi, Masahiro Murakawa, Tetsuya Higuchi (National Institute of Advanced
Industrial Science and Technology (AIST), Japan)
Coupled Support Vector Machines for Supervised Domain Adaptation
Hemanth Venkateswara (Arizona State University, USA), Prasanth Lade (Bosch Research and
Technology Center, USA), Jieping Ye (University of Michigan, USA), Sethuraman Panchanathan
(Arizona State University, USA)
Deep People Counting in Extremely Dense Crowds
Chuan Wang, Hua Zhang, Liang Yang, Si Liu, Xiaochun Cao (State Key Laboratory of Information
Security, Institute of Information Engineering, Chinese Academy of Sciences, China)
Gyro-based Camera-motion Detection in User-generated Videos
Sophia Bano (Queen Mary University of London; Polytechnic University of Catalonia, United
Kingdom), Andrea Cavallaro (Queen Mary University of London, United Kingdom), Xavier Parra
(Polytechnic University of Catalonia, Spain)
Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural
Networks
Wenchao Jiang, Zhaozheng Yin (Missouri University of Science and Technology, USA)
ACM Multimedia 2015 Conference
61
Wednesday 28 October
Image2Emoji: Zero-shot Emoji Prediction for Visual Media
Spencer Cappallo, Thomas Mensink (University of Amsterdam, Netherlands), Cees Snoek (University
of Amsterdam & Qualcomm Research Netherlands, The Netherlands)
Rich Image Description Based on Regions
Xiaodan Zhang (University of Chinese Academy of Sciences, City University of Hong Kong, China),
Xinhang Song, Xiong Lv, Shuqiang Jiang (Institute of Computing Technology, Chinese Academy of
Sciences, China), Qixiang Ye, Jianbin Jiao (University of Chinese Academy of Sciences, China)
Time:
16:00 – 17:30
Location:
Auditorium
Oral Session 4:
Multimedia and Vision
Session Chair:
Mohan S Kankanhalli (National University of Singapore, Singapore)
Dancing with Turks
I-Kao Chiang (University of Pennsylvania, USA), Ian Spiro (New York University, USA), Seungkyu
Lee (KyungHee University, South Korea), Alyssa Lees (New York University, USA), Jingchen Liu
(The Pennsylvania State University, USA), Chris Bregler (New York University, USA), Yanxi Liu (The
Pennsylvania State University, USA)
Single Image Spectral Reconstruction for Multimedia Applications
Antonio Robles-Kelly (NICTA, Australia)
SkyStitch: a Cooperative Multi-UAV-based Real-time Video Surveillance System with
Stitching
Xiangyun Meng, Wei Wang, Ben Leong (National University of Singapore)
Eye of the Dragon: Exploring Discriminatively Minimalist Sketch-based Abstractions for
Object Categories
Ravi Kiran Sarvadevabhatla, Venkatesh Babu R (Indian Institute of Science, India)
Time:
16:00 – 17:30
Location:
P6
Oral Session 5:
Multimedia Art, Entertainment and Culture
Session Chair:
James Wang (Pennsylvania State University, USA)
A Distributed Theatre Experiment with Shakespeare
Douglas L Williams, Ian C Kegel (BT, UK), Marian Ursu (University of York, UK), Pablo Cesar, Jack
Jansen (Centrum Wiskunde & Informatica, The Netherlands), Erik Geelhoed (Falmouth University, UK),
Andras Horti (Joanneum Research, Austria), Michael Frantzis (Goldsmiths, University of London, UK),
Bill Scott (Miracle Theatre Company, UK)
62
ACM Multimedia 2015 Conference
Wednesday 28 October
Image Profiling for History Events on the Fly
Jia Chen (Shanghai Jiao Tong University, China), Qin Jin (Renmin University of China), Yong Yu
(Shanghai Jiao Tong University, China), Alexander G. Hauptmann (Carneige Mellon University, USA)
Modeling Perspective Effects in Photographic Composition
Zihan Zhou, Siqiong He, Jia Li, James Z Wang (The Pennsylvania State University, USA)
Who’s Afraid of Itten: Using the Art Theory of Color Combination to Analyze Emotions in
Abstract Paintings
Andreza Sartori (University of Trento & Telecom Italia, Italy), Dubravko Culibrk (University of Trento,
Italy & University of Novi Sad, Serbia), Yan Yan, Nicu Sebe (University of Trento, Italy)
Time:
16:00 – 17:30
Location:
P7
Oral Session 6:
Telepresence, Virtual, and Augmented Reality
Session Chair:
Klara Nahrstedt (UIUC, USA)
Image2Scene: Transforming Style of 3D Room
Xiaowu Chen, Jianwei Li (Beihang University, China), Qing Li (Beijing Union University, China), Bo Gao,
Dongqing Zou, Qinping Zhao (Beihang University, China)
Gradient-based 2D-to-3D Conversion for Soccer Videos
Kiana Calagari (Simon Fraser University, Canada), Mohamed Elgharib (Qatar Computing Research
Institute, HBKU), Piotr Didyk (Saarland University, Germany), Alexandre Kaspar, Wojciech Matusik
(Massachusetts Institute of Technology, USA), Mohamed Hefeeda (Qatar Computing Research
Institute, HBKU)
Ubii: Towards Seamless Interaction between Digital and Physical Worlds
Zhanpeng Huang, Weikai Li, Pan Hui (Hong Kong University of Science and Technology, China)
Smart Beholder: An Open-Source Smart Lens for Mobile Photography
Chun-Ying Huang (National Taiwan Ocean University), Chih-Fan Hsu, Tsung-Han Tsai (Academia
Sinica, Taiwan), Ching-Ling Fan, Cheng-Hsin Hsu (National Tsing Hua University, Taiwan), Kuan-Ta
Chen (Academia Sinica, Taiwan)
ACM Multimedia 2015 Conference
63
Wednesday 28 October
Time:
16:00 – 17:30
Location:
P8
Oral Session 7:
Actions and Events
Session Chair:
Nicu Sebe (University of Trento, Italy)
Coherent Motion Detection with Collective Density Clustering
Yunpeng Wu, Yangdong Ye, Chenyang Zhao (Zhengzhou University, China)
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web
Images
Chen Sun (University of Southern California, USA), Sanketh Shetty, Rahul Sukthankar (Google, Inc.,
USA), Ram Nevatia (University of Southern California, USA)
Temporal Matching Kernel with Explicit Feature Maps
Sébastien Poullot (JFLI (CNRS), National Institute of Informatics, Japan), Shunsuke Tsukatani
(University of Tokyo, National Institute of Informatics, Japan), Anh Phuong Nguyen (MMLab –
University of Information Technology, Vietnam), Hervé Jégou (Inria, France), Shin’Ichi Satoh (National
Institute of Informatics, Japan)
Efficient Activity Retrieval through Semantic Graph Queries
Gregory Castanon, Yuting Chen, Ziming Zhang, Venkatesh Saligrama (Boston University, USA)
64
ACM Multimedia 2015 Conference
Thursday 29 October
Conference Day 3
Time:
9:00 – 10:30
Location:
Auditorium
Keynote:
Vision-enhanced Immersive Interaction and Remote Collaboration
with Large Touch Displays
Speaker:
Zhengyou Zhang (Microsoft Research, USA)
Chair:
Xiaofang Zhou (The University of Queensland, Australia)
Time:
11:00 – 16:00
Location:
P6 – P11 Foyer
Session:
Full/TOMM Paper Poster Session 3
Session Chair:
Xin-Shun Xu (Shandong University, China)
Analyzing Free-standing Conversational Groups: A Multimodal Approach
Xavier Alameda-Pineda, Yan Yan (University of Trento, Italy), Elisa Ricci, Oswald Lanz (Fondazione
Bruno Kessler, Italy), Nicu Sebe (University of Trento, Italy)
An Affordable Solution for Binocular Eye Tracking and Calibration in Head-mounted
Displays
Michael Stengel, Steve Grogorick (TU Braunschweig, Germany), Elmar Eisemann (TU Delft, The
Netherlands), Martin Eisemann (TH Koeln, Germany), Marcus A. Magnor (TU Braunschweig,
Germany)
SINGA: Putting Deep Learning in the Hands of Multimedia Users
Wei Wang (National University of Singapore), Gang Chen (Zhejiang university, China), Anh Tien Tuan
Dinh, Jinyang Gao, Beng Chin Ooi, Kian-Lee Tan, Sheng Wang (National University of Singapore)
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge
Propagation
Xiangbo Shu (Nanjing University of Science and Technolog, China), Guo-Jun Qi (University of Central
Florida, USA), Jinhui Tang (Nanjing University of Science and Technology, China), Jingdong Wang
(Microsoft Research, China)
ACM Multimedia 2015 Conference
65
Thursday 29 October
Fast and Accurate Content-based Semantic Search in 100M Internet Videos
Lu Jiang, Shoou-I Yu (Carnegie Mellon University, USA), Deyu Meng (Xi’an Jiaotong University, China),
Yi Yang (University of Technology Sydney, Australia), Teruko Mitamura, Alexander G Hauptmann
(Carnegie Mellon University, USA)
Visual Coding in a Semantic Hierarchy
Yang Yang (University of Electronic Science and Technology of China), Hanwang Zhang (National
University of Singapore), Mingxing Zhang, Fumin Shen (University of Electronic Science and
Technology of China), Xuelong Li (Chinese Academy of Sciences)
Deep Compositional Cross-modal Learning to Rank via Local-Global Alignment
Xinyang Jiang, Fei Wu, Xi Li, Zhou Zhao, Weiming Lu, Siliang Tang, Yueting Zhuang (Zhejiang
University, China)
Effective Multi-Query Expansions: Robust Landmark Retrieval
Yang Wang, Xuemin Lin (The University of New South Wales, Australia), Lin Wu (The University of
Adelaide, Australia), Wenjie Zhang (The University of New South Wales, Australia)
What are Popular: Exploring Twitter Features for Event Detection, Tracking and Visualization
Hongyun Cai (The University of Queensland, Australia), Yang Yang (University of Electronic Science
and Technology of China), Xuefei Li, Zi Huang (The University of Queensland, Australia)
Cross-Domain Collaborative Learning in Social Multimedia
Shengsheng Qian, Tianzhu Zhang (National Lab of Pattern Recognition, Institute of Automation, CAS,
China), Richang Hong (School of Computer and Information, Hefei University of Technology, China),
Changsheng Xu (National Lab of Pattern Recognition, Institute of Automation, CAS, China)
Learning Socially Embedded Visual Representation from Scratch
Shaowei Liu, Peng Cui, Wenwu Zhu, Shiqiang Yang (Tsinghua University, China)
Spatial-aware Multimodal Location Estimation for Social Images
Jiewei Cao, Zi Huang (The University of Queensland, Australia), Yang Yang (University of Electronic
Science and Technology of China)
Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach
Yang Hu, Xi Yi, Larry S. Davis (University of Maryland, USA)
Predicting and Understanding Urban Perception with Convolutional Neural Networks
Lorenzo Porzi (Fondazione Bruno Kessler, University of Perugia, Italy), Samuel Rota Bulò, Bruno Lepri
(Fondazione Bruno Kessler, Italy), Elisa Ricci (Fondazione Bruno Kessler, University of Perugia, Italy)
A Multimodal Predictive Model of Successful Debaters or How I Learned to Sway Votes
Maarten Brilman (University of Twente, The Netherlands), Stefan Scherer (USC Institute for Creative
Technologies, USA)
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology
Brendan Jou, Tao Chen (Columbia University, USA), Nikolaos Pappas (Idiap Research Institute,
Switzerland), Miriam Redi (Yahoo Labs, UK), Mercan Topkara (JW Player, USA), Shih-Fu Chang
(Columbia University, USA)
66
ACM Multimedia 2015 Conference
Thursday 29 October
Dancing with Turks
I-Kao Chiang (University of Pennsylvania, USA), Ian Spiro (New York University, USA), Seungkyu
Lee (KyungHee University, South Korea), Alyssa Lees (New York University, USA), Jingchen Liu
(The Pennsylvania State University, USA), Chris Bregler (New York University, USA), Yanxi Liu (The
Pennsylvania State University, USA)
Single Image Spectral Reconstruction for Multimedia Applications
Antonio Robles-Kelly (NICTA, Australia)
SkyStitch: a Cooperative Multi-UAV-based Real-time Video Surveillance System with
Stitching
Xiangyun Meng, Wei Wang, Ben Leong (National University of Singapore)
Eye of the Dragon: Exploring Discriminatively Minimalist Sketch-based Abstractions for
Object Categories
Ravi Kiran Sarvadevabhatla, Venkatesh Babu R (Indian Institute of Science, India)
A Distributed Theatre Experiment with Shakespeare
Douglas L Williams, Ian C Kegel (BT, UK), Marian Ursu (University of York, UK), Pablo Cesar, Jack
Jansen (Centrum Wiskunde & Informatica, The Netherlands), Erik Geelhoed (Falmouth University, UK),
Andras Horti (Joanneum Research, Austria), Michael Frantzis (Goldsmiths, University of London, UK),
Bill Scott (Miracle Theatre Company, UK)
Image Profiling for History Events on the Fly
Jia Chen (Shanghai Jiao Tong University, China), Qin Jin (Renmin University of China), Yong Yu
(Shanghai Jiao Tong University, China), Alexander G. Hauptmann (Carneige Mellon University, USA)
Modeling Perspective Effects in Photographic Composition
Zihan Zhou, Siqiong He, Jia Li, James Z Wang (The Pennsylvania State University, USA)
Who’s Afraid of Itten: Using the Art Theory of Color Combination to Analyze Emotions in
Abstract Paintings
Andreza Sartori (University of Trento & Telecom Italia, Italy), Dubravko Culibrk (University of Trento,
Italy & University of Novi Sad, Serbia), Yan Yan, Nicu Sebe (University of Trento, Italy)
Image2Scene: Transforming Style of 3D Room
Xiaowu Chen, Jianwei Li (Beihang University, China), Qing Li (Beijing Union University, China), Bo Gao,
Dongqing Zou, Qinping Zhao (Beihang University, China)
Gradient-based 2D-to-3D Conversion for Soccer Videos
Kiana Calagari (Simon Fraser University, Canada), Mohamed Elgharib (Qatar Computing Research
Institute, HBKU), Piotr Didyk (Saarland University, Germany), Alexandre Kaspar, Wojciech Matusik
(Massachusetts Institute of Technology, USA), Mohamed Hefeeda (Qatar Computing Research
Institute, HBKU)
Ubii: Towards Seamless Interaction between Digital and Physical Worlds
Zhanpeng Huang, Weikai Li, Pan Hui (Hong Kong University of Science and Technology, China)
ACM Multimedia 2015 Conference
67
Thursday 29 October
Smart Beholder: An Open-Source Smart Lens for Mobile Photography
Chun-Ying Huang (National Taiwan Ocean University, Taiwan), Chih-Fan Hsu, Tsung-Han Tsai
(Academia Sinica, Taiwan), Ching-Ling Fan, Cheng-Hsin Hsu (National Tsing Hua University, Taiwan),
Kuan-Ta Chen (Academia Sinica, Taiwan)
Coherent Motion Detection with Collective Density Clustering
Yunpeng Wu, Yangdong Ye, Chenyang Zhao (Zhengzhou University, China)
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web
Images
Chen Sun (University of Southern California, USA), Sanketh Shetty, Rahul Sukthankar (Google, Inc.,
USA), Ram Nevatia (University of Southern California, USA)
Temporal Matching Kernel with Explicit Feature Maps
Sébastien Poullot (JFLI (CNRS), National Institute of Informatics, Japan), Shunsuke Tsukatani
(University of Tokyo, National Institute of Informatics, Japan), Anh Phuong Nguyen (MMLab –
University of Information Technology, Vietnam), Hervé Jégou (Inria, France), Shin’Ichi Satoh (National
Institute of Informatics, Japan)
Efficient Activity Retrieval through Semantic Graph Queries
Gregory Castanon, Yuting Chen, Ziming Zhang, Venkatesh Saligrama (Boston University, USA)
Video Killed The Data Store: Extending the n-Dimensional Display Interface for Full Screen
Video
Charles D Estes, Ketan Mayer-Patel (University of North Carolina at Chapel Hill, USA)
Dependency-Aware Unequal Error Protection for Layered Video Coding
Mohammad Reza Zakerinasab, Mea Wang (University of Calgary, Canada)
HiFi: A Hierarchical Filtering Algorithm for Caching of Online Video
Shahid Akhtar, Andre Beck (Alcatel-Lucent, USA), Ivica Rimac (Alcatel-Lucent, Germany)
Exploring QoE for Power Efficiency: A Field Study on Mobile Videos with LCD Displays
Zhisheng Yan, Qian Liu (State University of New York at Buffalo, USA), Tong Zhang (Rensselaer
Polytechnic Institute, USA), Chang Wen Chen (State University of New York at Buffalo, USA)
Automatic Image Dataset Construction from Click-through Logs Using Deep Neural
Network
Yalong Bai (Harbin Institute of Technology, China), Kuiyuan Yang (Microsoft Research, China), Wei Yu
(Harbin Institute of Technology, China), Chang Xu (Nankai University, China), Wei-Ying Ma (Microsoft
Research, China), Tiejun Zhao (Harbin Institute of Technology, China)
DeepFont: Identify Your Font from An Image
Zhangyang Wang (UIUC, USA), Jianchao Yang (Snapchat Inc, USA), Hailin Jin, Eli Shechtman (Adobe
Research, USA), Aseem Agarwala (Google Inc, USA), Jonathan Brandt (Adobe Research, USA),
Thomas S. Huang (UIUC, USA)
68
ACM Multimedia 2015 Conference
Thursday 29 October
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video
Classification
Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, Xiangyang Xue (Fudan University, China)
EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video
Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang (Columbia University, USA)
Modelling Human Factors in Perceptual Multimedia Quality: On The Role of Personality and
Culture
Michael James Scott (Brunel University London, UK), Sharath Chandra Guntuku, Yang Huan, Weisi
Lin (Nanyang Technological University, Singapore), Gheorghita Ghinea (Brunel University London, UK)
Biologically Inspired Media Quality Modeling
Luming Zhang, Meng Wang (Hefei University of Technology, China), Liqiang Nie (National University
of Singapore), Richang Hong (Hefei University of Technology, China), Roger Zimmermann (National
University of Singapore), Yingjie Xia (Zhejiang University, China)
QoE Modelling for VP9 and H.265 Videos on Mobile Devices
Wei Song, Yao Xiao, Dian Tjondronegoro (Queensland University of Technology, Australia), Antonio
Liotta (Eindhoven University of Technology, The Netherlands)
Towards Solving the Bottleneck of Pitch-based Singing Voice Separation
Bilei Zhu, Wei Li, Linwei Li (Fudan University, China)
Enhancing the Quality of Interactive Multimedia Services by Proactive Monitoring and
Failure Prediction
Mohammed Shatnawi (Simon Fraser University, Canada), Mohamed Hefeeda (Qatar Computing
Research Institute, Hamad Bin Khalifa University)
Distributed Optimal Datacenter Bandwidth Allocation for Dynamic Adaptive Video
Streaming
Fanxin Kong (McGill University, Canada), Xingjian Lu (McGill University, Canada & East China
University of Science and Technology, China), Mingyuan Xia, Xue Liu (McGill University, Canada),
Haibing Guan (Shang Hai Jiao Tong University, China)
HTTP/2-Based Methods to Improve the Live Experience of Adaptive Streaming
Rafael Huysegems (Bell Labs, Belgium), Jeroen van der Hooft (Ghent University – iMinds, Belgium),
Tom Bostoen, Patrice Rondao Alface (Bell Labs, Belgium), Stefano Petrangeli, Tim Wauters, Filip De
Turck (Ghent University – iMinds, Belgium)
Bandwidth-aware Prefetching for Proactive Multi-video Preloading and Improved HAS
Performance
Vengatanathan Krishnamoorthi, Niklas Carlsson (Linköping University, Sweden), Derek Eager
(University of Saskatchewan, Canada), Anirban Mahanti (NICTA, Australia), Nahid Shahmehri
(Linköping University, Sweden)
Multi-View Visual Recognition of Imperfect Testing Data
Qilin Zhang, Gang Hua (Stevens Institute of Technology, USA)
ACM Multimedia 2015 Conference
69
Thursday 29 October
If You Can’t Beat Them, Join Them: Learning with Noisy Data
Pravin Kakar (Institute for Infocomm Research, Singapore), Alex Yong-Sang Chia (Rakuten Institute of
Technology, Singapore)
Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited
Supervision
Xiaojun Chang (University of Technology Sydney, Australia), Yao-Liang Yu (Carnegie Mellon University,
USA), Yi Yang (University of Technology Sydney, Australia), Alexander G. Hauptmann (Carnegie
Mellon University, USA)
Beyond Doctors: Future Health Prediction from Multimedia and Multimodal Observations
Liqiang Nie (National University of Singapore), Luming Zhang (Hefei University of Technology, China),
Yi Yang (University of Technology Sydney, Australia), Meng Wang, Richang Hong (Hefei University of
Technology, China), Tat-Seng Chua (National University of Singapore)
Multi-sensor Self-Quantification of Presentations
Tian Gan (National University of Singapore), Yongkang Wong (Interactive & Digital Media Institute,
Singapore), Bappaditya Mandal, Vijay Chandrasekhar (Institute for Infocomm Research, Singapore),
Mohan S. Kankanhalli (National University of Singapore)
HyperMeeting: Supporting Asynchronous Meetings with Hypervideo
Andreas Girgensohn, Jennifer Marlow (FX Palo Alto Laboratory, USA), Frank Shipman (Texas A&M
University, USA), Lynn Wilcox (FX Palo Alto Laboratory, USA)
MMToC: A Multimodal Method for Table of Content Creation in Educational Videos
Arijit Biswas, Ankit Gandhi, Om Deshmukh (Xerox Research Centre India, India)
Interactive Scene Flow Editing for Improved Image-based Rendering and Virtual Spacetime
Navigation
Kai Ruhl (TU Braunschweig, Germany), Martin Eisemann (TH Koeln, Germany), Anna Hilsmann, Peter
Eisert (HHI Fraunhofer, Germany), Marcus Magnor (TU Braunschweig, Germany)
CelebrityNet: A Social Network Constructed from Large Scale Online Celebrity Images
Li-Jia Li, David A. Shamma, Xiangnan Kong, Sina Jafarpour, Roelof Van Zwol, Xuanhui Wang (Yahoo!
Research, USA)
Similarity Search Over The Cloud Based On Dimensions Value Cardinalities
Stefanos Antaris, Dimitrios Rafailidis (Aristotle University of Thessaloniki, Greece)
Double Verification Secret Sharing Mechanism Based on Adaptive Pixel Pair Matching
Pei-Yu Lin (Yuan Ze University, Taiwan)
Wireless Multicast for Zoomable Video Streaming
Hui Wang, Mun Choon Chan, Wei Tsang Ooi (National University of Singapore)
QoE-Driven Rate Adaptation Heuristic for Fair Adaptive Video Streaming
Stefano Petrangeli (University in Ghent, Belgium), Jeroen Famaey (University in Antwerp, Belgium),
Maxim Claeys (University in Ghent, Belgium), Steven Latré (University in Antwerp, Belgium), Filip De
Turck (University in Ghent, Belgium)
70
ACM Multimedia 2015 Conference
Thursday 29 October
Multi-Camera Coordination and Control in Surveillance Systems: A Survey
Prabhu Natarajan (National University of Singapore), Pradeep K. Atrey (State University of
New York, USA), Mohan Kankanhalli (National University of Singapore)
Image Enhancement in Encrypted Domain over Cloud
Ankita Lathey (University of Winnipeg, Canada), Pradeep K. Atrey (University of Winnipeg, Canada
and State University of New York, USA)
Opinion Question Answering by Sentiment Clip Localization
Lei Pang, Chong-wah Ngo (City University of Hong Kong)
Improving Concept-Based Image Retrieval with Training Weights Computed from Tags
Vasileios Papapanagiotou, Christos Diou, Anastasios Delopoulos (Aristotle University of Thessaloniki,
Greece)
Time:
11:00 – 12:30
Location:
P6
Oral Session 8:
Video Systems
Session Chair:
Wu-Chi Feng (Portland State University, USA)
Video Killed The Data Store: Extending the n-Dimensional Display Interface for Full Screen
Video
Charles D Estes, Ketan Mayer-Patel (University of North Carolina at Chapel Hill, USA)
Dependency-Aware Unequal Error Protection for Layered Video Coding
Mohammad Reza Zakerinasab, Mea Wang (University of Calgary, Canada)
HiFi: A Hierarchical Filtering Algorithm for Caching of Online Video
Shahid Akhtar, Andre Beck, Ivica Rimac (Alcatel-Lucent, Germany)
Exploring QoE for Power Efficiency: A Field Study on Mobile Videos with LCD Displays
Zhisheng Yan, Qian Liu (State University of New York at Buffalo, USA), Tong Zhang (Rensselaer
Polytechnic Institute, USA), Chang Wen Chen (State University of New York at Buffalo, USA)
ACM Multimedia 2015 Conference
71
Thursday 29 October
Time:
11:00 – 12:30
Location:
P7
Oral Session 9:
Deep Learning and Multimedia
Session Chair:
Cees G M Snoek (University of Amsterdam & Qualcomm Research
Netherlands, The Netherlands)
Automatic Image Dataset Construction from Click-through Logs Using Deep Neural
Network
Yalong Bai (Harbin Institute of Technology, China), Kuiyuan Yang (Microsoft Research, China), Wei Yu
(Harbin Institute of Technology, China), Chang Xu (Nankai University, China), Wei-Ying Ma (Microsoft
Research, China), Tiejun Zhao (Harbin Institute of Technology, China)
DeepFont: Identify Your Font from An Image
Zhangyang Wang (UIUC, USA), Jianchao Yang (Snapchat Inc, USA), Hailin Jin, Eli Shechtman (Adobe
Research, USA), Aseem Agarwala (Google Inc, USA), Jonathan Brandt (Adobe Research, USA),
Thomas S. Huang (UIUC, USA)
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video
Classification
Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, Xiangyang Xue (Fudan University, China)
EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video
Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang (Columbia University, USA)
Time:
11:00 – 12:30
Location:
P8
Oral Session 10:
Multimedia Quality Perception
Session Chair:
Bart Thomee (Yahoo Research, USA)
Modelling Human Factors in Perceptual Multimedia Quality: On The Role of Personality and
Culture
Michael James Scott (Brunel University London, UK), Sharath Chandra Guntuku, Yang Huan, Weisi
Lin (Nanyang Technological University, Singapore), Gheorghita Ghinea (Brunel University London, UK)
Biologically Inspired Media Quality Modeling
Luming Zhang, Meng Wang (Hefei University of Technology, China), Liqiang Nie (National University
of Singapore), Richang Hong (Hefei University of Technology, China), Roger Zimmermann (National
University of Singapore), Yingjie Xia (Zhejiang University, China)
QoE Modelling for VP9 and H.265 Videos on Mobile Devices
Wei Song, Yao Xiao, Dian Tjondronegoro (Queensland University of Technology, Australia),
Antonio Liotta (Eindhoven University of Technology, The Netherlands)
72
ACM Multimedia 2015 Conference
Thursday 29 October
Towards Solving the Bottleneck of Pitch-based Singing Voice Separation
Bilei Zhu, Wei Li, Linwei Li (Fudan University, China)
Time:
11:00 – 12:30
Location:
Auditorium
Session:
Art Exhibit Presentations
Chairs:
Ann Morrison (Aalborg University, Denmark) Stephen Viller (The University
of Queensland, Australia)
Using Handmade Controllers for Interactive Projection Mapping
Alinta K. Krauth (Griffith University, Australia)
3D Printing and Camera Mapping: Dialectic of Virtual and Reality
He-Lin Luo, Yi-Ping Hung (National Taiwan University) I-Chun Chen (Taipei National University of the
Arts, Taiwan)
Drag A Star – the Social Media in Outer Space
James She (Hong Kong University of Science & Technology) Cameron Ng (JM Network, Hong Kong)
Desmond Leung (Desmond Leung Media Arts, Hong Kong)
Disturbed System: Recreating Sculptor’s Experience of Their Medium With Haptics and
Generated Sound
Oksana Krzyhanivska, Simon Fay, Jeffrey E. Boyd (University of Calgary, Canada)
The Real Time Rolling Shutter
David S. Monaghan, Noel E. O’Connor (Dublin City University, Ireland) Anne Cleary, Denis Connolly
(Independent artists, France)
Time:
11:00 – 16:00
Location:
P10 – P11
Session:
Art Exhibit
Time:
12.30 – 14:00
Location:
Auditorium and Foyer
Session:
Award Ceremony and SIGMM Business Lunch
Chair:
Shih-Fu Chang (SIGMM Chair)
ACM Multimedia 2015 Conference
73
Thursday 29 October
Time:
14:00 – 15:30
Location:
Auditorium
Panel:
Opportunities and Challenges of Industry-Academic Collaborations in
Multimedia Research— Industry Trends and Perspectives
Chairs:
Shih-Fu Chang (Columbia University, USA) and David A. Shamma (Yahoo
Labs, USA)
Panelists:
Matt Cooper (FXPal, USA) Denver Dash (Magic Leap, USA) Funda KivranSwaine (Facebook, USA) Jia Li (Snapchat, USA)
There have been several rapid advancements in large-scale multimedia computing in the past 5
years. As the sheer volume of online photos and other multimedia data has increased and there
have been recent optimizations in deep learning; many industry technologies have become the
focus of research, application, and press. However, there is much that remains unsolvable and that
is likely beyond industrial reach. In this panel, we aim to illuminate the hard questions for the future
as well as discuss the intersections and collaboration opportunities that exist to bridge and grow the
vital communities across both academia and industry. Given the vibrant participation from industry,
ACMMM is the natural community for industry and academia to jointly explore this intersection topic.
A panel with such focus will help ACMMM to continue its preeminent position in leading such fruitful
joint efforts. We aim for this panel to be discussion lead with four industry recognized panelists from
a diverse background as not to just skew to a single multimedia perspective. The two organizers will
carry the conversation and questions forward and invite audience discussion and participation from
the start.
Time:
14:00 – 15:30
Location:
P6
Oral Session 11:
Multimedia Networking
Session Chair:
Ketan Mayer-Patel (University of North Carolina, USA)
Enhancing the Quality of Interactive Multimedia Services by Proactive Monitoring and
Failure Prediction
Mohammed Shatnawi (Simon Fraser University, Canada), Mohamed Hefeeda (Qatar Computing
Research Institute, Hamad Bin Khalifa University)
Distributed Optimal Datacenter Bandwidth Allocation for Dynamic Adaptive Video
Streaming
Fanxin Kong (McGill University, Canada), Xingjian Lu (McGill University, Canada & East China
University of Science and Technology), Mingyuan, Xue Liu (McGill University, Canada), Haibing Guan
(Shang Hai Jiao Tong University, China)
74
ACM Multimedia 2015 Conference
Thursday 29 October
HTTP/2-Based Methods to Improve the Live Experience of Adaptive Streaming
Rafael Huysegems (Bell Labs, Belgium), Jeroen van der Hooft (Ghent University – iMinds, Belgium),
Tom Bostoen, Patrice Rondao Alface (Bell Labs, Belgium), Stefano Petrangeli, Tim Wauters, Filip De
Turck (Ghent University – iMinds, Belgium)
Bandwidth-aware Prefetching for Proactive Multi-video Preloading and Improved HAS
Performance
Vengatanathan Krishnamoorthi, Niklas Carlsson (Linköping University, Sweden), Derek Eager
(University of Saskatchewan, Canada), Anirban Mahanti (NICTA, Australia), Nahid Shahmehri
(Linköping University, Sweden)
Time:
14:00 – 15:30
Location:
P7
Oral Session 12:
Data Imperfectness for Multimedia
Session Chair:
Meng Wang (Hefei Institute of Technology, China)
Multi-View Visual Recognition of Imperfect Testing Data
Qilin Zhang, Gang Hua (Stevens Institute of Technology, USA)
If You Can’t Beat Them, Join Them: Learning with Noisy Data
Pravin Kakar (Institute for Infocomm Research, Singapore), Alex Yong-Sang Chia (Rakuten Institute of
Technology, Singapore)
Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited
Supervision
Xiaojun Chang (University of Technology Sydney, Australia), Yao-Liang Yu (Carnegie Mellon University,
USA), Yi Yang (University of Technology Sydney, Australia), Alexander G. Hauptmann (Carnegie
Mellon University, USA)
Beyond Doctors: Future Health Prediction from Multimedia and Multimodal Observations
Liqiang Nie (National University of Singapore), Luming Zhang (Hefei University of Technology, China),
Yi Yang (University of Technology Sydney, Australia), Meng Wang, Richang Hong (Hefei University of
Technology, China), Tat-Seng Chua (National University of Singapore)
ACM Multimedia 2015 Conference
75
Thursday 29 October
Time:
14:00 – 15:30
Location:
P8
Oral Session 13:
Multimedia Experiences and Expectations
Session Chair:
Dick C A Bulterman (FXPAL, USA)
Multi-sensor Self-Quantification of Presentations
Tian Gan (National University of Singapore), Yongkang Wong (Interactive & Digital Media Institute,
Singapore), Bappaditya Mandal, Vijay Chandrasekhar (Institute for Infocomm Research, Singapore),
Mohan S. Kankanhalli (National University of Singapore)
HyperMeeting: Supporting Asynchronous Meetings with Hypervideo
Andreas Girgensohn, Jennifer Marlow (FX Palo Alto Laboratory, USA), Frank Shipman (Texas A&M
University, USA), Lynn Wilcox (FX Palo Alto Laboratory, USA)
MMToC: A Multimodal Method for Table of Content Creation in Educational Videos
Arijit Biswas, Ankit Gandhi, Om Deshmukh (Xerox Research Centre India)
Interactive Scene Flow Editing for Improved Image-based Rendering and Virtual Spacetime
Navigation
Kai Ruhl (TU Braunschweig, Germany), Martin Eisemann (TH Koeln, Germany), Anna Hilsmann, Peter
Eisert (HHI Fraunhofer, Germany), Marcus Magnor (TU Braunschweig, Germany)
Time:
16:00 – 17:30
Location:
P8
Session:
MM-15 Exchange Meeting
76
ACM Multimedia 2015 Conference
Friday 30 October
Workshops
Workshop:
Multimedia COMMONS - Community-Organized Multimodal Mining:
Opportunities for Novel Solutions (MMCommons Workshop 2015)
Time:
9:00 – 17:00
Location:
Auditorium
8:30
Welcome Tea/Coffee (conference-wide)
9:00
MMCommons Workshop Welcome
9:05
Keynote Address
Alexander G. Hauptmann, Carnegie Mellon University
10:00
Plenary Session
Kickstarting the Commons: The YFCC100M, the YLI Corpus, and the Multimedia Commons
Introduction to the YFCC100M metadata corpus and to the Multimedia Commons datasets, which
contain computed features for the YFCC100M images and videos and subset annotations for research
tasks: location estimation (YLI-GEO) and event detection (YLI-MED). Presenters will summarize what’s in
the datasets, how they were collected, and how to get them.
10:30
Morning Tea Break (conference-wide)
11:00
Paper Session 1
Toward an Automatic Evaluation of Retrieval Performance with Large Scale Image Collections
Adrian Popescu, Eleftherios Spyromitros-Xioufis, Symeon Papadopoulos, Hervé Le Borgne, and Yiannis
Kompatsiaris (CEA LIST and CERTH-ITI)
Insights into Audio-Based Multimedia Event Classification with Neural Networks
Mirco Ravanelli, Benjamin Elizalde, Gerald Friedland, and Julia Bernd (FBK and ICSI)
Deep Classifiers from Image Tags in the Wild
Hamid Izadinia, Bryan Russell, Ali Farhadi, Matthew Hoffman, and Aaron Hertzmann (U. Washington and
Adobe)
Studying Object Naming with Online Photos and Captions
Alexander Mathews, Lexing Xie, and Xuming He (ANU and ICT Australia)
12:30
Lunch Break (conference-wide)
ACM Multimedia 2015 Conference
77
Friday 30 October
Multimedia COMMONS – Community-Organized Multimodal Mining: Opportunities for Novel
Solutions (MMCommons Workshop 2015) (continued)
13:30
Paper Session 2
Real-time Analysis and Visualization of the YFCC100M Dataset
Sebastian Kalkowski, Damian Borth, Christian Schulze, and Andreas Dengel (U. Kaiserslautern and DFKI)
Building User Profiles from Shared Photos
Dhiraj Joshi, Matthew Cooper, Francine Chen, and Yanying Chen (FXPAL)
14:15
Yahoo Grand Challenge Presenters on the YFCC100M
This year’s Yahoo Grand Challenge exemplified the potential of this new data to stimulate new
multimedia approaches: participants were asked to automatically detect, analyze the structure of, and
summarize events in the YFCC100M dataset.
15:00
Afternoon Tea Break (conference-wide)
15:30
Special Session on Annotations and Data Challenges
The instigators of the Multimedia Commons Project will facilitate a discussion about needs and
priorities for annotation of the YFCC100M dataset, including computed features and human-generated
annotations, and about possible structures for collecting and distributing these resources. This session
will include presentation of (a) straw-man proposal(s) for annotation plans and directed small-group
breakout discussions on special topics. Discussion throughout will be driven by consideration of
potential applications and of challenge problems and benchmarks that could serve as catalysts for
research.
16:55
Closing
For updates and changes, see www.mmcommons.org
78
ACM Multimedia 2015 Conference
Friday 30 October
Workshop:
ImmersiveMe-15: 3rd ACM International Workshop on Immersive Media
Experiences
Time:
9:00 – 17:00
Location:
P6
9:00
Welcome Address
9:15
Session 1 – Audiovisual Immersion and Enabling Technologies
Session Chair: Rene Kaiser, Joanneum Research, Graz, Austria
9:15
Content Adaptive Representations of Omnidirectional Videos for Cinematic Virtual Reality
Matt Yu, Haricharan Lakshman, Bernd Girod
9:40
Pan360: INS Assisted 360-Degree Panorama
Lun-Cheng Chu, Andre Chen, Yu-Hsin Lin, Yu-Mei Chen, Scott Chien-Hung Liao, Edward Y. Chang
10:05
Compressed Domain Video Processing for Tile Based Panoramic Streaming using SHVC
Yago Sanchez de La Fuente, Robert Skupin, Thomas Schierl
10:30
Morning Tea
11:00
Keynote Talk
Immersive Shared Experiences
Pablo Cesar, CWI: Centrum Wiskunde & Informatica, The Netherlands
Session Chair: Teresa Chambel, LaSIGE, F. Ciências, Univ. de Lisboa, Portugal
12:30
Lunch Break
13:30
Session 2 – Collaborative and Participatory Scenarios in Augmented Reality
Session Chair: Pablo Cesar, CWI, The Netherlands
13.30
Enabling Distributed Theatre Performances through Multi-Camera Telepresence – Capturing System
Behaviour in a Script-Based Approach
Rene Kaiser, Marian F. Ursu, Manolis Falelakis, Andras Horti
13:55
3D Collaboration Method over HoloLens and Skype End Points
Austin Lee, Henry Chen, Mark Swift, John Tang
14:10
Session 3 – Human Aspects in Immersive Media Experiences
Session Chair: Teresa Chambel, LaSIGE, F. Ciências, Univ. de Lisboa, Portugal
14:10
Immersive Interactive Technologies in Digital Humanities: A Review and Basic Concepts
Artur Lugmayr, Marko Teras
14:35
Measuring Audience Responses of Video Advertisements Using Phisiological Sensors
Chen Wang, Pablo Cesar
15:00
Afternoon Tea
15:30
Demos and Discussion – Immersive Media: experiences and perspectives
16:45
Wrap Up
ACM Multimedia 2015 Conference
79
Friday 30 October
Workshop:
CrowdMM 2015 - Fourth International ACM Workshop on
Crowdsourcing for Multimedia
Time:
9:00 – 17:00
Location:
P7
9:00
Welcome and intro from the chairs
9:30
Keynote Address
Words and Pictures – Crowdsource Discovery beyond Image Semantics
Prof. Shih-Fu Chang (Columbia University)
10:30
Coffee break
11:00
Oral Session
11:00
Paper 08
Eye tracker in the wild: Studying the delta between what is said and measured in a
crowdsourcing experiment
Pierre Lebreton* (Technische Universität Berlin ); Isabelle Hupont (UPMC – Sorbonne Universities); Toni
Mäki (VTT Technical Research Centre of Finland); Evangelos Skodras (University of Patras); Matthias
Hirth (University of Wuerzburg)
11:25
Paper 06
Bridging the Utilitarian-Hedonic Divide in Crowdsourcing Applications
Mark Melenhorst* (Delft University of Technology); Jasminko Novak (European Institute for Participatory
Media); Isabel Micheel (European Institute for Participatory Media); Martha Larson (Delft University of
Technology); Martin Boeckle (European Institute for Participatory Media)
11:50
Paper 09
Do Scale-Design and Training Matter for Video QoE Assessments through Crowdsourcing?
Bruno Gardlo* (The Telecommunications Research Center Vienna); Sebastian Egger (AIT); Tobias Hossfeld
(University Essen-Duisburg)
12:15
Lunch
14:00
Poster Madness Session – 3 minutes per paper
80
ACM Multimedia 2015 Conference
Friday 30 October
14:15
Poster presentations
Paper 01
Generation of a video summary on a news topic based on SNS responses to news stories
Kosuke Kato (Nagoya University); Ichiro Ide (Nagoya University); Daisuke Deguchi (Nagoya University);
Hiroshi Murase (Nagoya University)
Paper 02
Why Design Matters – Crowdsourcing of Complex Tasks
Baar Winther (Simula); Lilian Calvet (Simula); Carsten Griwodz (Simula); Pål Halvorsen (Simula); Michael
Riegler* (Simula Research Laboratory)
Paper 10
When the crowd challenges the lab: lessons learnt from subjective studies on image aesthetic
appeal
Judith Redi* (Delft University of Technology); Ernestasia Siahaan (Delft University of Technology); Pavel
Korshunov (EPFL); Julian Habigt (Technical University Munich); Tobias Hossfeld (University EssenDuisburg)
Paper 12
Impact of tone-mapping algorithms on subjective and objective face recognition in HDR images
Pavel Korshunov* (EPFL); Marco Bernardo (UBI); Touradj Ebrahimi (EPFL); Antonio Pinheiro (UBI)
15:30
Coffee Break
16:00
CrowdKeynote! (see crowdmm.org/crowdkeynote/ to learn how to contribute)
17:00
Discussion and Conclusion session
ACM Multimedia 2015 Conference
81
Friday 30 October
Workshop:
ASM-15: The 1st International Workshop on Affect and Sentiment in
Multimedia
Time:
9:00 – 17:00
Location:
P9
9:00-11:00
Opening session
Chair: Mohammad Soleymani (University of Geneva)
9:00-9:50
Keynote 1
Blending Users, Content, and Emotions for Movie Recommendations,
Shlomo Berkovsky (CSIRO)
9:50-10:30
Oral session 1: Audio analysis
9:50-10:10
Learning combinations of multiple feature representations for Music Emotion Prediction
Jens Madsen (DTU); Bjørn Jensen (DTU); Jan Larsen (DTU)
10:10-10:30
Twitter: A New Online Source of Automatically Tagged Data for Conversational Speech Emotion
Recognition
Christopher Hines (UNSW); Julien Epps (UNSW); Vidhyasaharan Sethu (UNSW)
10:30-11:00
Coffee break
11:00-12:20
Oral session 2Content Analysis
Chair: Yu-Gang Jiang (Fudan University)
11:00-11:20
Affect recognition in a realistic movie dataset using a hierarchical approach
Diana Affi (Uni. Applied Sci.); Joël Dumoulin (Uni. Applied Sci.); Marco Bertini (Uni. Florence);
Elena Mugellini (Uni. Applied Sci.); Omar Abou Khaled (Uni. Applied Sci.); Alberto Del Bimbo
(University of Florence)
11:20-11:40
Do others perceive you as you want them to? Modeling Personality based on Selfies
Sharath Chandra Guntuku (Nanyang Tech. Uni.); Lin Qiu (Nanyang Tech. Uni.); Sujoy Roy (Inst.
Infocomm Research) ; Weisi Lin (Nanyang Tech. Uni.); Vinit Jakhetiya (Hong Kong Uni. Sci. Tech.)
11:40-12:00
Aesthetic Photo Enhancement using Machine Learning and Case-Based Reasoning
Joachim Folz (DFKI); Christian Schulze (DFKI); Damian Borth (DFKI); Andreas Dengel (DFKI)
12:00-12:20
Prediction of User Ratings of Oral Presentations using Label Relations
Toshihiko Yamasaki (Uni. Tokyo); Ryosuke Furuta (Uni. Tokyo); Yusuke Fukushima (Uni. Tokyo);
Litian Sun (Uni. Tokyo); Kiyoharu Aizawa (Uni. Tokyo); Danushka Bollegala (Uni. Liverpool)
12:20-13:50
Lunch break
82
ACM Multimedia 2015 Conference
Friday 30 October
13:50-14:40
Keynote 2: Nicole Nelson
Chair: Yu-Gang Jiang (Fudan University)
14:40-15:50
Oral session 3: Applications
Chair: Yu-Gang Jiang (Fudan University)
14:40-15:00
Continuous Arousal Self-assessments Validation Using Real-time Physiological Responses
Ting Li (Technicolor); Yoann Baveye (Technicolor & Ecole Centrale de Lyon); Christel Chamaret
(Technicolor); Emmanuel Dellandréa (Ecole Centrale de Lyon); Liming Chen (Ecole Centrale de
Lyon)
15:00-15:30
Coffee break
15:30-15:50
An Interactive System based on Yes-No Questions for Affective Image Retrieval,
Saemi CHOI (Uni. Tokyo); Toshihiko Yamasaki (Uni. Tokyo); Kiyoharu Aizawa (Uni. Tokyo)
15:50:16:30
Oral session 4: Sentiment analysis
Chair: Shih-Fu Chang (Columbia University)
15:50:16:10
What makes a Beautiful Landscape beautiful: Adjective Noun Pairs Attention by Eye-Tracking and
Gaze Analysis
Syed Saqib Bukhari (DFKI); Damian Borth, (DFKI); Mohammad Al Naser (DFKI); Andreas Dengel
(DFKI); Saleh Mozafari (DFKI)
16:10-16:30
Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction
Victor Campos (UPC); Amaia Salvador (UPC); Brendan Jou (Columbia University); Xavier Giró (UPC)
16:30:17:00
Panel: Multimedia Sentiment Analysis - what, why and who?
Moderator: Mohammad Soleymani
ACM Multimedia 2015 Conference
83
Friday 30 October
Workshop:
2nd Workshop on Computational Models of Social Interactions:
Human-Computer-Media Communication (HCMC2015)
Time:
9:00 – 17:00
Location:
P8
9:00
Session 1
9:00
Opening (10 minutes)
9:10
Keynote Speaker: Lexing Xie
Can a video be promoted? a generative model for social media popularity
9:50
Keynote Speaker: Alberto Del Bimbo
Natural Interaction Metaphors for Personalized Multimedia Museum Experiences
10:30
Coffee break
11:00
Session 2
11:00
Keynote Speaker: Ajay Divakaran
Human Social Interaction Sensing and Modeling
11.40
Keynote Speaker: Vivek Singh
Sensing and Shaping Human Behavior using Multimodal Signals
12:20
Lunch
13:20
Session 3
13:20
Keynote Speaker: Mohan Kankanhalli
Social Interactions and Presentation Analytics
14:00
Workshop paper: Wei-Ta Chu
Event Detection and Highlight Detection of Broadcasted Game Videos
14:20
Workshop paper: Muhammad Khan
Expressive Multimedia: Bringing Action to Physical World by Dancing-Tablet
14:40
Workshop paper: Mukesh Saini
Multimedia Fatigue Detection for Adaptive Infotainment User Interface
15:00
Coffee break
15:30
Session 4
15:30
Workshop paper: Reza Shoja Ghiass, Ognjen Arandjelovic, Denis Laurendeau
Highly Accurate and Fully Automatic Head Pose Estimation from a Low Quality Consumer-Level RGB-D
Sensor
15:50
Workshop paper: Sheetal Takale
How Flickr Helps to Know the Place: Visual and Textual Summarization of Geo-location
16:10
Demo Session and Panel Discussion
84
ACM Multimedia 2015 Conference
Friday 30 October
Workshop:
2015 Workshop on Speech, Language and Audio in Multimedia –
SLAM15
Time:
9:00 – 17:00
Location:
P10
9:00
Workshop introduction
9:15
Keynote
David Dean, Queensland University of Technology
SAIVT-BNEWS: An Australian broadcast news video dataset of entity extraction, and more
10:15
Coffee break
10:45
Morning Session
10:45
Predicting music popularity patterns based on musical complexity and early stage popularity
Junghyuk Lee and Jong-Seok Lee (Yonsei University, Korea)
11:15
Speaker LDA: Discovering Topics in Transcribed Multi-Speaker Audio Contents
Damiano Spina, Johanne R. Trippas, Lawrence Cavedon and Mark Sanderson (RMIT University, Australia)
11:45
Acoustic adaptation in cross database audio visual SHMM training for phonetic spoken term detection
Shahram Kalantari, David Dean, Sridha Sridharan, Houman Ghaemmaghami and Clinton Fookes (QUT,
Australia)
12:15
Evaluation Data, Benchmarks, and Activities for Cascaded Speech Recognition and Extraction of 35
Entities: Content Capturing, Segmentation, and Structuring of Verbal Clinical Handover
Liyuan Zhou, Hanna Suominen and Leif Hanlen (National ICT Australia, Australia)
Poster
Score Propagation based on Similarity Shot Graph for Improving Visual Object Retrieval
Juan Manuel Barrios and Jose M. Saavedra (ORAND Chile S.A., Chile)
12:45
Lunch break
14:00
Hyperlinking session : Vision meets speech and language
14:00
Convenient Discovery of Archived Video Using Audiovisual Hyperlinking
Roeland Ordelman (Univ. of Twente & Netherlands Institute for Sound and Vision), Robin Aly (Univ. of
Twente, The Netherlands) , Maria Eskevich, Benoît Huet (EURECOM, France) and Gareth Jones (Dublin
City University, Ireland
14:30
Audio Information for Hyperlinking of TV content
Petra Galuščáková and Pavel Pecina (Univerzita Karlova v Praze, Czech Republic)
15:00
Hierarchical topic models for language-based video hyperlinking
Anca-Roxana Simon, Guillaume Gravier, Pacale Sébillot (INSA Rennes, IRISA & Inria Rennes, France),
Rémi Bois (CNRS, IRISA & Inria Rennes, France), Emmanuel Morin (Univ. Nantes, LINA, France) and Sien
Moens (KU Leuven, Belgium)
15:30
Exploring Video Hyperlinking in Broadcast Media
Maria Eskevich, Quoc-Minh Bui, Hoang-An and Benoît Huet (EURECOM, France)
16:00
Round table discussion
17:00
Close
ACM Multimedia 2015 Conference
85
Friday 30 October
Workshop:
Human-centred Event Understanding from Multimedia –
HuEvent 2015
Time:
9:00 – 12.30
Location:
P11
Keynote Speaker
Cees Snoek – Recognizing events in videos without examples
In this talk I will present recent progress on recognizing events in videos, without the need for
examples. The key to event recognition in such a challenging setting is to have a lingual video
representation. Three lingual representations for zero-example event recognition will be highlighted,
covering concept, tag and sentence embeddings.
Workshop Papers
Tingting Yao, Zhiyong Wang, Zhao Xie, Jun Gao and David Dagan Feng.
Discovering Commonness and Specificness for Human Action Recognition
Maia Zaharieva and Michael Riegler.
Media Synchronization and Sub-Event Detection in Multi-User Image Collection
Konstantinos Apostolidis and Vasileios Mezaris.
Using Photo Similarity and Weighted Graphs for the Temporal Synchronization of EventCentered Multi-User Photo Collections
86
ACM Multimedia 2015 Conference
Social Program
Conference Reception and Art Exhibit Opening
Date:
Tuesday 27 October
Time:
18:00 – 20:00
Location:
P10 – P11, Foyer and North Terrace, Brisbane Convention & Exhibition
Centre
Conference Banquet
Date:
Wednesday 28 October
Time:
18:00 – 21:00
Location:
Brisbane City Hall, King George Square, Brisbane City
ACM Multimedia 2015 Conference
87
MM 2015 Conference Organization
and Committees
Conference Organization
General Chairs
Xiaofang Zhou (The University of Queensland, Australia)
Alan Smeaton (Dublin City University, Ireland)
Qi Tian (The University of Texas at San Antonio, USA)
Technical Program Committee Chairs
Dick C.A. Bulterman (FXPAL, USA)
Heng Tao Shen (The University of Queensland, Australia)
Ketan Mayer-Patel (The University of North Carolina, USA)
Shuicheng Yan (National University of Singapore, Singapore)
Author’s Advocate
Wei Tsang Ooi (National University of Singapore, Singapore)
Brave New Idea Chairs
Yong Rui (Microsoft Research Asia, China)
Nicu Sebe (University of Trento, Italy)
Xuelong Li (OPTical IMagery Analysis and Learning (OPTIMAL), China)
Multimedia Grand Challenge Chairs
Michael Lew (Leiden University, The Netherlands)
Jie Yang (National Science Foundation, USA)
Technical Demo Chairs
Alejandro Jaimes (Yahoo!, Spain)
Zheng-Jun Zha (Hefei Institute of Intelligent Machines, Chinese
Academy of Sciences)
Interactive Arts Chairs
Stephen Viller (The University of Queensland, Australia)
Ann Morrison (Aalborg University, Denmark)
Panel Chairs
Chang Wen Chen (University at Buffalo, USA)
Zhi-Hua Zhou (Nanjing University, China)
Open Source Software Competition
Chairs
Xian-Sheng Hua (Microsoft, USA)
Marco Bertini (University of Florence, Italy)
Tao Mei (Microsoft Research, China)
Video Program Chairs
Shin’ichi Satoh (National Institute of Informatics, Japan)
Meng Wang (Hefei University of Technology, China)
Jinman Kim (The University of Sydney, Australia)
Doctoral Symposium Chairs
Cees G. M. Snoek (University of Amsterdam & Qualcomm Research
Netherlands, The Netherlands)
Hervé Jégou (Facebook AI Research, France)
88
ACM Multimedia 2015 Conference
Tutorials Chairs
Rainer Lienhart (University of Augsburg, Germany)
Thomas Plagemann (University of Oslo, Norway)
Zhiyong Wang (The University of Sydney, Australia)
Workshop Chairs
Alan Hanjalic (Delft University of Technology, The Netherlands)
Lexing Xie (Australian National University, Australia)
Svetha Venkatesh (Deakin University, Australia)
Sponsorship Chairs
Abdulmotaleb EI Saddik (University of Ottawa, Canada)
Rong Yan (Snapchat Inc, USA)
Kiyoharu Aizawa (University of Tokyo, Japan)
Zhengyou Zhang (Microsoft Research, USA)
Travel Grant Chairs
Xiangjian (Sean) He (University of Technology Sydney, Australia)
Yang Yang (University of Electronic Science and Technology, China)
Publicity Chairs
Jiebo Luo (University of Rochester, USA)
Lei Zhang (Microsoft Research, USA)
Weidong Cai (The University of Sydney, Australia)
History Preservation Chairs
K. Selçuk Candan (Arizona State University, USA)
Chong-Wah Ngo (City University of Hong Kong, Hong Kong)
Local Organization Chairs
Xue Li (University of Queensland, Australia)
Dian Tjondronegoro (Queensland University of Technology, Australia)
Finance Chair
Zi Huang (The University of Queensland, Australia)
Proceedings Chairs
Roger Zimmermann (National University of Singapore, Singapore)
Yongdong Zhang (Chinese Academy of Science, China)
Web and Social Media Chairs
Lorna Macdonald (The University of Queensland, Australia)
Jun Zhou (Griffith University, Australia)
ACM Multimedia 2015 Conference
89
MM 2015 Area Chairs
Multimedia Telepresence and Virtual/
Augmented Reality
Klara Nahrstedt (UIUC, USA)
Wanmin Wu (Ricoh Innovations, USA)
Multimedia Systems and Middleware
Wu-Chi Feng (Portland State University, USA)
Kuan-Ta Chen (Academia Sinica, Taiwan)
Multimedia Transport and Delivery
Ali C. Begen (Cisco Systems, USA)
Christian Timmerer (Alpen-Adria-University Klagenfurt, Austria)
Mobile Multimedia
Jochen Huber (MIT Media Lab, USA)
Winston Hsu (National Taiwan University, Taiwan)
Multimedia for Collaboration in
Education & Distributed Environments
Matt Cooper (FXPAL, USA)
Multimedia HCI and Quality of
Experience
Bart Thomee (Yahoo, USA)
Music, Speech and Audio Processing in
Multimedia
Ye Wang (National University of Singapore, Singapore)
Multimedia Authoring and Enrichment
Pablo Cesar (CWI, The Netherlands)
Deep Learning for Multimedia
Greg Corrado (Google, USA)
Ming Yang (Facebook, USA)
Multimodal Analysis and Description
Mohan S. Kankanhalli (National University of Singapore, Singapore)
Xian-Sheng Hua (Microsoft Research, USA)
Qiong Liu (FXPAL, USA)
Guo-Jun Qi (University of Central Florida, USA)
Benoit Huet (Eurecom, France)
Multimedia and Vision
Nicu Sebe (University of Trento, Italy)
Gang Hua (Stevens Institute of Technology, USA)
Yaser Sheikh (CMU, USA)
Meng Wang (Hefei Institute of Technology, China)
Cees G. M. Snoek (University of Amsterdam & Qualcomm Research
Netherlands, The Netherlands)
Multimedia Art, Entertainment and
Culture
James Z. Wang (Pennsylvania State University, USA)
Vincent Oria (New Jersey Institute of Technology, USA)
Multimedia Search and
Recommendation
John R. Smith (IBM, USA)
Jingdong Wang (Microsoft Research Asia, China)
Phoebe Chen (University of Latrobe, Australia)
Chunhua Shen (Adelaide University, Australia)
Zi Huang (University of Queensland, Australia)
Social Multimedia
Mei Tao (Microsoft Research Asia, China)
Peng Cui (Tsinghua University, China)
Emotional and Social Signals In
Multimedia
Hayley Hung (Technical University of Delft, The Netherlands)
Hatice Gunes (Queen Mary University of London, UK)
Mohammad Soleymani (University of Geneva, Switzerland)
Emily Mower Provost (University of Michigan, USA)
90
ACM Multimedia 2015 Conference
MM 2015 Program Committee
Abhinav Dhall
Aisling Kelliher
Aixin Sun
Ajita John
Albert Ali Salah
Alexander Raake
Ali C. Begen
Amirhossein Habibian
Amy Pavel
Andreas Girgensohn
Andrew Hines
Andrew Jones
Andrew Maas
Andrew Perkis
Anna Hilsmann
Arefin Ahsan
Arnold Smeulders
Arslan Basharat
Balakrishnan Prabhakaran
Baochun Li
Bart Thomee
Benoit Huet
Benoit Favre
Bin Cui
Bin Li
Bingbing Ni
Björn W. Schuller
Brais Martinez
Bruce Thomas
Bruno Lepri
Caifeng Shan
Carl James Debono
Carl S. Marshall
Carsten Griwodz
Cathal Gurrin
Cees G. M. Snoek
Cha Zhang
Changsheng Xu
Cheng Deng
Cheng-Hsin Hsu
Chenqiang Gao
Chong-Wah Ngo
Christian Timmerer
Christoph Trattner
Christopher Peters
Chunhua Shen
Chun-Ying Huang
Cynthia Liem
Cyril Concolato
Dacheng Tao
Damian Borth
Daniel Overholt
Daragh Byrne
David Grunberg
David Imseng
Deyu Meng
Dhiraj Joshi
Dinesh Jayagopi
Dong Liu
Eakta Jain
Eckehard Steinbach
Eduardo Veas
Emily Mower Provost
Eng-Jon Ong
Erik Mannens
Fei Wu
Feiping Nie
Felix Yu
Feng Zheng
Fernando Pereira
Florian Metze
Fons Kuijk
Francesc Alias
Frank Nack
Frank Shipman
Fred Charles
Fumin Shen
Gang Hua
Gene Cheung
George Tzanetakis
Gerald Friedland
Go Irie
Graham Percival
Greg Corrado
Gregorij Kurillo
Grenville Armitage
Gualtiero Volpe
Guillaume Chanel
Guillaume Gravier
Guo-Jun Qi
Guosheng Lin
Gustavo Carneiro
Gwendal Simon
Haichao Zhang
Hamid Izadinia
Hanwang Zhang
Hao Tang
Haoxiang Li
Harald Wuest
Hari Sundaram
Hatice Gunes
Hayley Hung
Hayrettin Gurkok
Herman Engelbrecht
Hong Lu
Houqiang Li
Huan Li
Huchuan Lu
Huiyu Zhou
Ian Kegel
Ichiro Ide
Ilaria Bartolini
Ishan Vaishnavi
Jacopo Staiano
James Wang
Jan van Gemert
Jan Willem Kleinrouweler
Jasper Uijlings
Jean-Charles Bazin
Jenny Benois-Pineau
Jeremy R. Cooperstock
Jiajun Liu
Jialie Shen
ACM Multimedia 2015 Conference
91
MM 2015 Program Committee (continued)
Jianbing Shen
Jianfei Cai
Jiang Wang
Jiangtao Cui
Jianmin Li
Jie Shao
Jiebo Luo
Jim Vaughan
Jingdong Wang
Jinhui Tang
Jinqiao Wang
Jitao Sang
Jochen Huber
John Kender
John R. Smith
John Tang
Joke Kort
Jonathan Ventura
Jonghwa Kim
Jordi Luque
Jörg Ott
Jose Alvarez
Ju Fan
Judith Redi
Juergen Geiger
Jun Zhou
Junfeng He
Jungong Han
Junping Zhang
Junsong Yuan
Kaiming He
Kathy Clawson
Kazuhiro Otsuka
Kazuya Takeda
Ke Hu
Ketan Mayer-Patel
Kevin Almeroth
Kevin Gao
Khiet Truong
Khurram Soomro
Klara Nahrstedt
92
Kuan-Ta Chen
Lamberto Ballan
Laurent Amsaleg
Lea Skorin-Kapov
Lei Chen
Lei Zhang
Lianli Gao
Lie Lu
Lijun Zhang
Ling Shao
Lingfen Sun
Lingqiao Liu
Litao Yu
Longfei Zhang
Lu Jiang
Luca Aiello
Lucjan Janowski
Luming Zhang
Luoqi Liu
Lynda Hardman
Lyndon Kennedy
Maha Abdallah
Marc Cavazza
Marcel Worring
Marcio Ferreira Moreno
Marco Cristani
Maria da Graca Campo
Pimentel
Maria-Luisa Sapino
Marianna Obrist
Mario Montagud
Mark Cartwright
Mark Claypool
Mark Hasegawa-Johnson
Mark Liao
Marko Tkalcic
Markus Schedl
Martha Larson
Marwin Schmitt
Massimo Piccardi
Mathew Magimai Doss
ACM Multimedia 2015 Conference
Mathias Lux
Matt Cooper
Maurizio Mancini
Meihui Zhang
Meng Wang
Michael Gurevich
Michel Valstar
Michele Merler
Ming Li
Ming Yang
Mingkui Tan
Mingli Song
Mingsong Dou
Mohamed Chetouani
Mohamed Hefeeda
Mohammad Soleymani
Mohan S. Kankanhalli
Mu Qiao
Munmun De Choudhury
Nabil Sarhan
Nadia Berthouze
Nicholas Race
Nicu Sebe
Niloo Dezfuli
Nitendra Rajput
Noel C. F. Codella
Oliver Nina
Omar Niamut
Oya Celiktutan
Pablo Cesar
Pål Halvorsen
Paris Smaragdis
Pascal Mettes
Patrick Lucey
Pavel Korshunov
Pei-Yu Chi
Peng Cui
Peng Wang
Peter Bajcsy
Peter Carr
Peter Grosche
Philipp Fechteler
Phoebe Chen
Pinar Duygulu Sahin
Preeti Rao
Qi Wang
Qiong Liu
Ram Vasudevan
Raoul Rivas
Raphael Troncy
Raymond Fu
Reid Porter
Remi Trichet
Rene Kaiser
Richang Hong
Rodrigo Laiola Guimarães
Roger Zimmermann
Ronald Poppe
Rongrong Ji
Rufael N. Mekuria
Saad Ali
Sabina Barakovic
Salman Khokhar
Samira Ebrahimi Kahou
Sean Banerjee
Shang-Hong Lai
Shannon Chen
Shervin Shirmohammadi
Shiguang Shan
Shih-Fu Chang
Shin’ichi Satoh
Shoou-I Yu
Shu Shi
Si Liu
Sileye Ba
Songqing Chen
Sorin Hermon
Stavros Petridis
Stefanos Vrochidis
Stefanos Zafeiriou
Stephan Kopf
Stevan Rudinac
Steven Hoi
Surender Chandra
Susanne Boll
Suzanne Little
Symeon Papadopoulos
Tao Mei
Tat-Jen Cham
Teresa Chambel
Thomas Mensink
Thomas Steiner
Tiago Falk
Tim Althoff
Ting Yu
Tobias Hossfeld
Touradj Ebrahimi
Ulrich Engelke
Vasileios Mezaris
Vincent Oria
Vittorio Baroncini
Wanmin Wu
Wei Liu
Wei Tong
Wei Tsang Ooi
Wei Wang
Wengang Zhou
Wen-Hsiao Peng
Wen-Huang Cheng
Winston H. Hsu
Wolfgang Huerst
Wu-Chi Feng
Xi Li
Xiangyang Xue
Xian-Sheng Hua
Xiaofei He
Xiaofeng Zhu
Xiaoqiang Lu
Xinbo Gao
Xin-Jing Wang
Xinmei Tian
Xin-shun Xu
Xirong Li
Xubo Yang
Xueliang Liu
Xuelong Li
Yadong Mu
Yahong Han
Yan Tong
Yan Yan
Yang Yang
Yannis Kalantidis
Yanwei Pang
Yan-Ying Chen
Yao Hu
Yao Liu
Yao Zhao
Yaser Sheikh
Yashar Moshfeghi
Ye Wang
Yelin Kim
Yi Li
Yi Yang
Yiannis Kompatsiaris
Yi-Hsuan Yang
Yonggang Wen
Yoshiharu Ishikawa
Yue Ming
Yu-Gang Jiang
Yu-Hsun Lin
Zan Gao
Zheng Liu
Zheng-Jun Zha
Zhenxing Niu
Zhenyang Li
Zhenzhong Lan
Zhifeng Li
Zhigang Ma
Zhiyong Wang
Zhongfei Zhang
Zhu Liu
Zi Huang
Zixia Huang
Zuofu Cheng
ACM Multimedia 2015 Conference
93
MM 2015 Brave New Idea Organization Committee
Chairs
Yong Rui (Microsoft Research Asia, China)
Nicu Sebe (University of Trento, Italy)
Xuelong Li (OPTical IMagery Analysis and Learning (OPTIMAL), China)
Program Committee
Abdulmotaleb El Saddik (University of Ottawa, Canada)
Benoit Huet (Eurecom, France)
Bo Du (Wuhan University, China)
Bo Luo (University of Kansas, USA)
Bruno Lepri (FBK, Italy)
Cha Zhang (Microsoft Research, USA)
Cheng Deng (Xidian University, China)
Chong-Wah Ngo (Hong Kong University of Science & Technology, Hong Kong)
Dong Liu (Columbia University, USA)
Gene Cheung (National Institute of Informatics, Japan)
Gerald Friedland (International Computer Science Institute, USA)
Jacopo Staiano (UPMC-Sorbonne Universitees, France)
Jian Zhang (University of Technology Sydney, Australia)
Jianfei Cai (Nanyang Technological University, Singapore)
Jiebo Luo (University of Rochester, USA)
Kaiqi Huang (Chinese Academy of Sciences, China)
Kuan-Ta Chen (Academia Sinica, Taiwan)
Lei Zhang (Microsoft Research Asia, China)
Lexing Xie (Australian National University, Australia)
Ling Shao (Northumbria University, UK)
Lyndon Kennedy (Yahoo Labs, USA)
Marco Cristani (University of Verona, Italy)
MarthaLarson (TU Delft, Netherlands)
Mohammad Soleymani (University of Geneva, Switzerland)
94
ACM Multimedia 2015 Conference
Munmun De Choudhury (Georgia Tech, USA)
Nannan Wang (Xidian University, China)
Peng Cui (Tsinghua University, China)
Ramanathan Subramanian (Advanced Digital Sciences Center, Singapore)
Raymond Fu (Northeastern University, USA)
Shin’ichi Satoh (National Institute of Informatics, Japan)
Stefan Winkler (Advanced Digital Sciences Center, Singapore)
Tao Mei (Microsoft Research Asia, China)
Ting Yao (Microsoft Research Asia, China)
Vasileios Mezaris (CERTH-ITI, Greece)
Winston Hsu (National Taiwan University, Taiwan)
Xian-Sheng Hua (Microsoft Research, USA)
Xiaogang Wang (The Chinese University of Hong Kong, Hong Kong)
Xing Xie (Microsoft Research Asia, China)
Yi Yang (University of Technology Sydney, Australia)
Yongsheng Dong (Chinese Academy of Sciences, China)
ACM Multimedia 2015 Conference
95
MM 2015 Doctoral Symposium Program Committee
Chairs
Cees G. M. Snoek (University of Amsterdam & Qualcomm Research Netherlands, The
Netherlands)
Hervé Jégou (Facebook AI Research, France)
Program Committee
Relja Arandjelovic (Inria, France)
Susanne Boll (University of Oldenburg, Germany)
Dick Bulterman (FXPAL, USA)
Shih-Fu Chang (Columbia University, USA)
Tat-Seng Chua (National University of Singapore, Singapore)
Alan Hanjalic (Delft University of Technology, The Netherlands)
Xian-Sheng Hua (Alibaba Group, China)
Alexis Joly (Inria, France)
Thomas Mensink (University of Amsterdam, The Netherlands)
Bernard Merialdo (Eurecom, France)
Dinh Phung (Deakin University, Australia)
Georges Quénot (Laboratory of Informatics of Grenoble, France)
Miriam Redi (Yahoo! Research, UK)
Shin’ichi Satoh (NII, Japan)
Ronan Sicre (Inria, France)
Giorgos Tolias (Inria, France)
Lexing Xie (Australian National University, Australia)
96
ACM Multimedia 2015 Conference
MM 2015 Grand Challenge Program Committee
Chairs
Michael Lew (Leiden University, The Netherlands)
Jie Yang (National Science Foundation, USA)
Program Committee
IBM – New York City 360°
John Smith (IBM, USA)
Liangliang Cao (IBM,USA)
Michele Merler (IBM, USA)
Yuan-Chi Chang (IBM,USA)
Microsoft – MSR-Bing Image Retrieval Challenge
Hongzhi Li (Columbia University, USA)
Yuxiao Hu (Microsoft, USA)
Zhangyang Wang (UIUC, USA)
Yahoo – Yahoo-Flickr Event Summarization Challenge
Adrian Popescu (CEA-LIST, France)
Bart Thomee (Yahoo Labs, USA)
Bogdan Ionescu (LAPI, University Politehnica of Bucharest, Romania)
Debanjan Mahata (University of Arkansas at Little Rock, USA)
Raphael Troncy (Eurecom, France)
Vasileios Mezaris (CERTH-ITI, Greece)
ACM Multimedia 2015 Conference
97
MM 2015 Technical Demos Program Committee
Chairs
Program Committee
98
Alejandro Jaimes (Yahoo!, Spain)
Zheng-Jun Zha (Hefei Institute of Intelligent Machines, Chinese Academy of Sciences)
Marco Beritini (ESADE, Spain)
Junjie Cai (University of Texas at San Antonio, USA)
Yang Cao (University of Science and Technology of China, China)
Shu-Ching Chen (Florida International University, USA)
Jian Chen (Institute of Automation, CAS, China)
Wen-Huang Cheng (Academia SINICA, Taiwan)
Cheng Deng (Xidian University, China)
Lu Fang (University of Science and Technology of China, China)
Alex Hauptman (Carnegie-Mellon University, USA)
Steven Hoi (Singapore Management University, Singapore)
Wolfgang Hurst (Utrecht University, Netherlands)
Ichiro Ide (Nagoya University, Japan)
Alejandro Jaimes (Yahoo!, USA)
Yannis Kalantidis (Yahoo!, USA)
Yiannis Kompatsiaris (Informatics and Telematics Institute, Greece)
Hyowon Lee (Singapore University of Technology and Design, Singapore)
Liang Li (University of Chinese Academy of Sciences, China)
Dong Liu (University of Science and Technology of China, China)
Vasileios Mezaris (CERTH-ITI, Greece)
Bingbing Ni (Advanced Digital Sciences Center, Singapore)
Naoko Nitta (Osaka University, Japan)
Vincent Oria (New Jersey Institute of Technology, USA)
Stefan Rueger (The Open University, UK)
Jitao Sang (Institute of Automation, CAS, China)
Shin’ichi Satoh (National Institute of Informatics, Japan)
Klaus Schoeffmann (Klagenfurt University, Austria)
Xinmei Tian (University of Science and Technology of China, China)
Changhu Wang (Microsoft Research Asia, China)
Qi Wang (Northwestern Polytechnical University, China)
Jinqiao Wang (Institute of Automation, CAS, China)
Xiangyu Wang (Institute for Infocomm Research, Singapore)
Zilei Wang (University of Science and Technology of China, China)
Marcel Worring (University of Amsterdam, Netherlands)
ACM Multimedia 2015 Conference
Program Committee
(continued)
Yang Yang (University of Electronic Science and Technology of China)
Kuiyuan Yang (Microsoft Research Asia, China)
Xin Yang (Huazhong University of Science and Technology, China)
Ting Yao (Microsoft Research Asia, China)
Zheng-Jun Zha (Hefei Institute of Intelligent Machines, CAS, China)
Hanwang Zhang (National University of Singapore, Singapore)
Shiliang Zhang (Beijing University, China)
Yan-Tao Zheng (Snapchat Inc., USA)
Wengang Zhou (University of Science and Technology of China, China)
Roger Zimmermann (National University of Singapore, Singapore)
MM 2015 Interactive Art Organization Committee
Chairs
Program Committee
Stephen Viller (University of Queensland, Australia)
Ann Morrison (Aalborg University, Denmark)
Anna Cicognani (GeoOp, University of Wollongong, Australia)
David Cranswick (Gallery, Shoalhaven City Council, Australia)
Line Marie Bruun Jespersen (Art & Technology, Aalborg University, Denmark)
Julianne Pierce (Chair of Arts Practice, Australia Council for the Arts, Australia)
Gavin Sade (Queensland University of Technology, Australia)
Nathaniel Stern (University of Johannesburg, Gallery AOP, South Africa, & Tory Folliard
Gallery, University of Wisconsin, USA)
ACM Multimedia 2015 Conference
99
MM 2015 Open Source Software Competition Organization
Committee
Chairs
Program Committee
Marco Bertini (University of Florence, Italy)
Xian-Sheng Hua (Alibaba, China)
Tao Mei (Microsoft Research Asia, China)
Andreas Girgensohn (FXPAL, USA)
Anthony Vetro (Mitsubishi Electric Research Laboratories, USA)
Samson Cheung (University of Kentucky, USA)
Steven Hoi (Singapore Management University, Singapore)
Peng Cui (Tsinghua University, China)
Chia-Wen Lin (National Tsing Hua University, Taiwan)
Dan Ellis (Columbia University, USA)
Meng Wang (Hefei University of Technology, China)
Junfeng He (Facebook, USA)
Ichiro Ide (Nagoya University, Japan)
Yangqing Jia (Google, USA)
Jingdong Wang (Microsoft Research Asia, China)
Rongrong Ji (Xiamen University, China)
Kuiyuan Yang (Microsoft Research Asia, China)
Lei Zhang (Microsoft Research, USA)
Liangliang Cao (Yahoo! Labs, USA)
Qiong Liu (FXPAL,USA)
Marco Bertini (University of Florence, Italy)
Ioannis Pitas (University of Thessaloniki, Greece)
Kuan-Ta Chen (Academia Sinica, Taiwan)
Kwang-Ting (Tim) Cheng (University of California, Santa Barbara, USA)
Vicky Zhao (University of Alberta, Canada)
Winston Hsu (National Taiwan University, Taiwan)
Lynn Wilcox (FXPAL, USA)
Xiaoyan Sun (Microsoft Research Asia, China)
Yan-Yin Chen (FXPAL, USA)
Yi Yang (University of Technology, Sydney, Australia)
Yimin Zhang (Intel, China)
Yu-Gang Jiang (Fudan University, China)
Zhou Wang (University of Waterloo, Canada)
100 ACM Multimedia 2015 Conference
Registration and
Information Desk
Location:
Auditorium Foyer
Open:
7:00 – 21:00, Monday 26 October
7:00 – 20:00, Tuesday 27 October
8:00 – 18:00, Wednesday 28 October
8:00 – 18:00, Thursday 29 October
7:00 – 17:00, Friday 30 October
Event Coordinator:
Kathleen Williamson
Phone: 0401 477 509
Email:
info2015@acmmm.org
Volunteers
Volunteers will be available to help with any questions during the conference. They may be identified
by their bright blue MM-15 shirts.
MM-15 would like to extend our warm appreciation to our conference volunteers who assisted
before, during and after the conference, to help make sure that everyone enjoys a great conference
experience. These volunteers welcome participants, give directions, help in the sessions and on the
registration desk, and generally make sure the conference is running smoothly.
Internet Access
Wireless internet access is available for delegates attending the MM-15 conference who have their
own laptops. For instructions on how to access the wireless network, please see the volunteers at
the MM-15 registration desk.
Handy Brisbane Apps
Including AirTrain, bikes, taxis, public transport, maps, news, weather and food:
choosebrisbane.com.au/conventions/how-we-can-help/convention-support-toolkit/enhancingdelegate-experience/brisbane-tourist-apps
ACM Multimedia 2015 Conference 101
Transport
How to travel to/from airport and venue
TRAIN: The Airtrain runs to/from Brisbane Domestic and International Airports, with travel time of just
25 minutes to South Brisbane Station, a short walk to the Brisbane Convention & Exhibition Centre. A
one-way single adult ticket costs AUD16.00.
For the Airtrain timetable please visit airtrain.com.au
Weekends: Airport to South Brisbane Station – First train 6am – Last train 22:00
South Brisbane Station to Airport – First train 5am – Last train 21:00
Mon–Fri: Airport to South Brisbane Station – First train 5.40am – Last train 22:00
South Brisbane Station to Airport – First train 5am – Last train 21:00
TAXI: Fares vary due to distance, traffic conditions and time, however, you can anticipate that a fare
to/from Brisbane’s CBD and Brisbane Airport will total approximately AUD50.00.
Public Transport in Brisbane – Buses, Trains and Ferries
For timetables and other details, go to: translink.com.au
go card is TransLink’s electronic ticket. It allows you to travel seamlessly on all bus, train and ferry
services. Buy your go card at most news agencies or online via
https://gocard.translink.com.au/webtix/
102 ACM Multimedia 2015 Conference
MM 2015 Sponsors
Sponsors
Gold Sponsors
MM 2015 Sponsors
Silver Sponsors
Bronze Sponsors
Supporter
102617/OMCGatton/ October2015