Welcome to VCAE2010, July 8-10, 2010, Xi'an, China
|
Prof. Shipeng Li,
Microsoft Research Asia
The Trends in
Multimedia Computing
Prof.
Chong-Wah
Ngo,
City University of Hong Kong
Online Editing of
Lecture Videos by Integrating Posture, Gesture and Text
Prof.
Qi Tian,
The University of Texas at San Antonio, USA
Building Contextual
Visual Vocabulary for Large-scale Image Applications
Prof.
Xiansheng Hua,
Microsoft Research Asia
Content-Based
Multimedia Technologies ¨C A Collection of Demonstrations from MSRA
Prof.
Jiebo Luo,
Kodak Research Laboratories, USA
Prof.
Ming Zhou,
Microsoft Research Asia
Prof.
Feng Wu,
Microsoft Research Asia
Prof.
Nicu Sebe,
University of Trento, Italy
Prof. Tat-Seng
Chua,
National
University of Singapore
Prof.
Shuicheng Yan,
National University of Singapore
Prof.
Ling Shao,
The University of Sheffield, UK
¡¡
|
Invited Speakers and Abstracts of Speeches:
| ¡¡ |
Title: The
Trends in Multimedia Computing
Speaker: Shipeng Li, Ph.D.,
Principal Researcher/Research Area Manager, Media Computing Group,
Microsoft Research Asia
Abstract: With the rapid
development of Web 2.0 and cloud computing concept and applications,
there are many unprecedented web-based multimedia applications are
emerging today and they pose many new challenges in multimedia
research. In this talk, I first summarize the common features of the
new wave of multimedia applications which I call Media 2.0. I use 6
D¡¯s to describe Media 2.0 principles, namely, Democratized media
life cycle; Data-driven media value chain; Decoupled media system;
Decomposed media contents; Diminished media boundary between
physical and virtual world, and Decentralized media business model.
Then I explain what the implications of Media 2.0 to multimedia
research are and how we should choose our research topics that could
make big impacts. Finally, I use example research projects ranging
from media codecs, media systems, media search and media related
advertisement from MSRA to demonstrate the ideas I have talked
about. I hope these ideas and principles could inspire the audience
to come up with new media 2.0 research topics and applications in
the future.
Bio of Speaker: Dr. Shipeng Li joined Microsoft Research
Asia (MSRA) in May 1999. He is now a Principal Researcher and
Research Manager of the Media Computing group. He also serves as the
Research Area Manager coordinating the multimedia research
activities at MSRA. His research interests include Signal and Image
Processing; Content-based Analysis; Image and Video Coding; HDTV
Technology; Multimedia Streaming and Communications over Internet
and Wireless Networks; Scalable Multimedia Representation;
Application Level Multicast; Digital Right Management; Wireless
Communication and Networking; P2P Networking; New Media Formats and
Systems; Media Advertisement; eHealth; and User Intent Mining. From
Oct. 1996 to May 1999, Dr. Li was with Multimedia Technology
Laboratory at Sarnoff Corporation (formerly David Sarnoff Research
Center, and RCA Laboratories) as a Member of Technical Staff. Dr. Li
has been actively involved in research and development in broad
multimedia areas. He has made several major contributions adopted by
MPEG-4 and H.264 standards. He invented and developed the world
first cost-effective high-quality legacy HDTV decoder in 1998. He
started P2P streaming research at MSRA as early as in August 2000.
He led to build the first working scalable video streaming prototype
across the Pacific Ocean in 2001. He has been an advocate of
scalable coding format and is instrumental to the SVC extension of
H.264/AVC standard. He first proposed the 6 ¡°D¡± Media 2.0concepts
that outlined the new directions of next generation internet media
research (2006). He has authored and co-authored over 200 journal
and conference papers and holds 83 granted and 90+ pending US
patents in image/video processing, compression and communications,
digital television, multimedia and wireless communication. He is the
co-author of book chapter ¡°MPEG-4 Texture Coding¡± in ¡°Multimedia
Systems and Standards¡± published by the Marcel Dekker, Inc. (2000),
the principal author of book chapter ¡°Image and Video Coding¡± in
¡°The Wiley Encyclopedia of Telecommunications¡± published by the
Wiley and Sons, Inc (2003), a co-author of book chapter ¡°Scalable
Video Coding for Adaptive Streaming Applications¡± in ¡°Multimedia
over IP and Wireless Networks¡± published by Academic Press (2007), a
co-author of book ¡°Video Technology¡± published by USTC press (2009).
He is a co-editor of ¡°Proceedings of Visual Communications and Image
Processing 2005¡± published by SPIE (2005), and a co-editor of
Lecture Notes in Computer Science: Advances in Multimedia
Information Processing - PCM 2008 published by Springer (2008).
Dr. Li is a Senior Member of IEEE. He the current chair of Visual
Signal Processing and Communications technical committee, a member
of Multimedia Systems and Applications technical committee, of IEEE
Circuits and Systems Society. He is a member of Multimedia
Communication technical committee of IEEE Communication Society and
a past member of Multimedia Signal Processing technical committee of
IEEE Signal Processing Society. He serves as an associate editor of
IEEE Transactions on Circuits and Systems for Video Technologyand is
on the editorial board of Journal of Visual Communications and Image
Representation. He was a special session/tutorial chair of IEEE PCM
2000, a local arrangement chair of IEEE PCM 2001, a technical
program chair for VCIP 2005, a general chair of Packet Video 2006, a
track chair of ICME 2006, a publicity chair of IEEE ISM 2006, a
theme chair of IEEE PSIVT 2006, an award chair of IEEE SiPS 2007, a
special session chair of IEEE ICME 2007, a program chair of PCM 2008
and a track chair of ISCAS 2009. He is a general chair of VCIP 2010
and a general chair of CIVR 2010. Dr. Li has also served or been
serving in over a dozen technical committees of various
international conferences on multimedia.
Dr. Li holds guest or adjunct professorships in Sichuan University,
Shandong University, Huazhong University of Science and Technology,
Shanghai Jiaotong University, the Chinese University of Hong Kong,
Nankai University, and Tianjin University, respectively. He is also
PhD supervisors for University of Science and Technology of China
and Shanghai Jiaotong University.
Dr. Li received his B.S. and M.S. in Electrical Engineering from the
University of Science and Technology of China (USTC) in 1988 and
1991, respectively. He received his Ph.D. in Electrical Engineering
from Lehigh University, Bethlehem, PA, in 1996. He was assistant
professor in Electrical Engineering Department at University of
Science and Technology of China in 1991-1992.
Dr. Li was the only student in the history of University of Science
and Technology of China who had ever been awarded twice (1987 and
1991) the top honor ¨C Guo Mo Ruo Fellowship. He was also the first
recipient of double Sarnoff Technical Achievement Awards(Sarnoff,
1997) in a single year. Dr. Li received the Best Paper Awardat VCIP
2007, the Best Poster Paper Awardat MMSP 2008 and the Best Paper
Award in IEEE Transaction on Circuits and Systems for Video
Technology (2009). He also mentored his student to receive the Best
Student Paper Award in VCIP 2005. In his 10 years with MSRA, Dr. Li
has also incubated three MIT TR 35 Award Winners, including Qian
Zhang, Haitao Zheng, and Xian-Sheng Hua.
|
¡¡ |
| ¡¡ |
Title: Online Editing of
Lecture Videos by Integrating Posture, Gesture and Text
Speaker:
Prof.
Chong-Wah
Ngo,
City University of Hong Kong
Abstract:
Bio of Speaker: Chong-Wah
Ngo received his Ph.D in Computer Science from the
Hong Kong University of Science &
Technology (HKUST). He received his MSc and BSc, both in
Computer Engineering, from Nanyang
Technological University of Singapore. His research interests
are in multimedia search and computing. He has been serving the
technical program committees of numerous multimedia and information
retrieval conferences including ACM Multimedia (MM), ACM SIGIR,
International Conf. on Image and Video Retrieval (CIVR) and
International Conf. on Multimedia and Expo (ICME). In addition, he
is on the editorial board of Journal of Multimedia Data Engineering
and Management, and Journal of Advances in Multimedia. He is
founding leader of VIREO
(VIdeo REtrieval grOup). Currently, he also serves as the chairman
of ACM (Hong Kong Chapter).
Before joining CityU, he was a PhD
student under the supervision of
Prof. T. C. Pong
and Prof Roland Chin
in HKUST. He joined the research
group of
Prof Thomas Huang in
Beckman Institute as a post-doctoral visitor for a collaborative
project between UIUC and
HKUST during 2001. He also worked at
Information Technology Institute (ITI)
of Singapore in 1996, and as summer intern at
Microsoft Research
Asia in 1999.
He was born in Malaysia (Visit
Malaysia and then you will find the smile of people and the smile of
nature!). His hometown is at
Pekan
Nanas (a perfectly peaceful town), Pontian (the southest county
in Asia mainland), Johor, Malaysia. He studied in
Yu Ming (I) and
Foon Yew High School during
primary and secondary school time.
|
¡¡ |
| ¡¡ |
Title:
Building
Contextual Visual Vocabulary for Large-scale Image Applications
Speaker:
Prof. Qi Tian,
The University of Texas at San Antonio, USA
Abstract:
Not withstanding its great success and wide adoption in
Bag-ofvisual Words representation, visual vocabulary created from
single image local features is often shown to be ineffective largely
due to three reasons. First, many detected local features are not
stable enough, resulting in many noisy and non-descriptive visual
words in images. Second, single visual word discards the rich
spatial contextual information among the local features, which has
been proven to be valuable for visual matching. Third, the distance
metric commonly used for generating visual vocabulary does not take
the semantic context into consideration, which renders them to be
prone to noise. To address these three confrontations, we propose an
effective visual vocabulary generation framework containing three
novel contributions: 1) we propose an effective unsupervised local
feature refinement strategy; 2) we consider local features in groups
to model their spatial contexts; 3) we further learn a discriminant
distance metric between local feature groups, which we call
discriminant group distance. This group distance is further
leveraged to induce visual vocabulary from groups of local features.
We name it contextual visual vocabulary, which captures both the
spatial and semantic contexts. We evaluate the proposed local
feature refinement strategy and the contextual visual vocabulary in
two large-scale image applications: large-scale near-duplicate image
retrieval on a dataset containing 1.5 million images and image
search re-ranking tasks. Our experimental results show that the
contextual visual vocabulary shows significant improvement over the
classic visual vocabulary. Moreover, it outperforms the
state-of-the-art Bundled Feature in the terms of retrieval
precision, memory consumption and efficiency.
Bio of Speaker:
Qi Tian
is currently an Associate Professor in the Department of Computer
Science, the University of Texas at San Antonio (UTSA). During
2008-2009, he took one-year Faculty Leave at Microsoft Research Asia
(MSRA) in the Media Computing Group (former Internet Media Group) as
Lead Researcher. He received his Ph.D. in 2002 from University of
Illinois at Urbana-Champaign, and his B.E. degree in 1992 from
Tsinghua University. Dr. Tian¡¯s research interests include
multimedia information retrieval and computer vision. He has
published about 110 refereed journal and conference papers in these
fields. His research projects were funded by ARO, DHS, HP Lab, SALSI,
CIAS, and CAS. He was the co-author of a Best Student Paper in
ICASSP 2006, and co-author of a Best Paper Candidate in PCM 2007. He
was a nominee for 2008 UTSA President Distinguished Research Award.
He received ACM Service Award in 2010. He has been serving as
Program Chairs, Organization Committee Members, Session Chairs and
TPC for over 120 IEEE and ACM Conferences including ACM Multimedia,
SIGIR, ICCV, ICME, ICASSP, ICPR, MIR, VCIP, PCM, etc. He is the
funding member of International Steering Committee of ACM
International Conference on Multimedia Retrieval (ICMR), and ACM
Multimedia Conference Review Committee Member. He is the Associate
Editor of IEEE Transactions on CSVT, Guest co-Editors of IEEE
Transactions on Multimedia, Journal of Computer Vision and Image
Understanding, and EURASIP Journal on Advances in Signal Processing
and is in the Editorial Board of Journal of Multimedia. He is a
Senior Member of IEEE (2003), and a Member of ACM (2004). He
currently holds Guest Professorship Position at University of
Science and Technology of China (USTC), Zhejiang University and
Xidian University, China, respectively.
|
¡¡ |
| ¡¡ |
Title:
Content-Based Multimedia Technologies ¨C A Collection of
Demonstrations from MSRA
Speaker:
Prof. Xinsheng Hua,
Lead Researcher, Media Computing Group, Microsoft Research Asia
Abstract:
Bio of Speaker: Xian-Sheng
Hua received the B.S. and Ph.D. degrees from Peking University,
Beijing, China, in 1996 and 2001, respectively, both in applied
mathematics. Since 2001, he has been with Microsoft Research Asia,
Beijing, where he is currently a Lead Researcher with the media
computing group. His current research interests are in the areas of
video content analysis, multimedia search, management, authoring,
sharing, mining, advertising and mobile multimedia computing. He has
authored or co-authored more than 180 publications in these areas
and has more than 50 filed patents or pending applications. He is
now an adjunct professor of University of Science and Technology of
China, and serves as an Associate Editor of IEEE Trans. on
Multimedia, Associate Editor of ACM Trans. on Intelligent Systems
and Technology, Editorial Board Member of Advances in Multimedia and
Multimedia Tools and Applications, and editor of Scholarpedia
(Multimedia Category). Dr. Hua won the Best Paper Award and Best
Demonstration Award in ACM Multimedia 2007, Best Poster Award in
2008 IEEE International Workshop on Multimedia Signal Processing,
Best Student Paper Award in ACM Conference on Information and
Knowledge Management 2009, and Best Paper Award in International
Conference on MultiMedia Modeling 2010. He also won 2008 MIT
Technology Review TR35 Young Innovator Award for his outstanding
contribution in enhancing video search, and named as one of the
Business Elites of People under 40 to Watch by Global Entrepreneur.
¡¡ |
¡¡ |
| ¡¡ |
¡¡ |
¡¡ |
|
