ACM MM 2011

Keynote 2: "U are happy life": telling the future's stories

Speaker: Genevieve Bell, Intel Labs

Abstract: To be announced

Bio: Bell joined Intel in 1998 as a researcher in Corporate Technology Group's People and Practices Research team — Intel's first social science oriented research team. She helped drive the company's first non-U.S. field studies to inform business group strategy and products and conducted groundbreaking work in urban Asia in the early 2000s. Bell has been the driving force behind Intel’s emerging user-experience focus: over the last decade, she has fundamentally changed how Intel envisions, plans, and develops its platforms.
Bell currently leads an R&D team of social scientists, interaction designers, human factors engineers, and a range of technology researchers to create the next generation of compelling user experiences across a range of internet-connected devices, platforms, and services. She will drive user-centered experience and design across the compute continuum.
Prior to joining Intel, Bell was a lecturer in the Department of Anthropology at Stanford University. She has written more than 25 journal articles and book chapters on a range of subjects focused on the intersection of technology and society. Her book, "Divining the Digital Future," co-authored with Prof. Paul Dourish, will be released by MIT Press in spring 2011.
Raised in Australia, Bell received her bachelor's degree in anthropology from Bryn Mawr College in 1990. She received her master's and doctorate degrees in anthropology from Stanford University in 1993 and 1998, respectively.

Back to Overview

---

Oral Session Day 2

Research 5: Media transport and sharing Session Chair: Roger Zimmerman
Towards Peer-Assisted Rendering in Netwroked Virtual Environments	Minhui Zhu*, NUS; Wei Tsang Ooi, ; Sebastien Mondet, ; Geraldine Morin, ; Wei Cheng,
BlueStreaming: Towards Power-Efficient Internet P2P Streaming to Mobile Devices	Yao Liu*, George Mason University; Fei Li, ; Lei Guo, ; Yang Guo, Bell Labs; Songqing Chen, George Mason University
Peer-assisted Texture Streaming in Metaverses	Ke Liang*, National Univ. of Singapore; Roger Zimmermann, National University of Singapore; Wei Tsang Ooi,
Cloud Download: Using Cloud Utilities to Achieve High-quality Content Distribution for Unpopular Videos	Yan Huang, Tencent Research; Zhenhua Li*, Peking University; Gang Liu, Tencent Research; Yafei Dai, Peking University

Research 6: Media authoring and production Session Chair: Frank Nack, University of Amsterdam
Generating Story Variants with Constrained Video Recombination	Alberto Piacenza, ; Fabrizio Guerrini*, University of Brescia; Nicola Adami, ; Riccardo Leonardi, ; Jonathan Teutenberg, ; Julie Porteous, ; Marc Cavazza , University of Teesside
Personalizing Automated Image Annotation using Cross-Entropy	Xirong Li*, University of Amsterdam; Efstratios Gavves, ; Cees Snoek, University of Amsterdam; Marcel Worring, University of Amsterdam; Arnold Smeulders,
Cross Media Hyperlinking for Search Topic Browsing	Song Tan*, City University of Hong Kong; Chong Wah Ngo, City University of Hong Kong; HungKhoon Tan, ; Lei Pang,
Creating Personalized Memories from Social Events: Community-Based Support for Multi-Camera Recordings of School Concerts	Rodrigo Laiola Guimaraes*, CWI; Pablo Cesar , CWI; Dick Bulterman, ; Vilmos Zsombori, Goldsmiths College; Ian Kegel, BT Research & Technology

Research 7: Media analysis and search Session Chair: Qi Tian, UTSA
Towards Multi-Semantic Image Annotation with Graph Regularized Exclusive Group Lasso	Xiangyu Chen*, NUS; Xiaotong Yuan, ; Shuicheng Yan, NUS; Jinhui Tang, Nanjing University of Science and Technology; Yong Rui, Microsoft Asia; Tat-Seng Chua, National Univ of Singapore
Reading between the Tags to Predict Real-World Size-Class for Visually Depicted Objects in Images	Martha Larson*, Delft University of Technology; Christoph Kofler, Delft University of Technology; Alan Hanjalic, TU Delft
Exploiting the Entire Feature Space with Sparsity for Automatic Image Annotation	Zhigang Ma*, University of Trento; Yi Yang, ; Feiping Nie, ; Jasper Uijlings, Univ. of Trento; Nicu Sebe,
Colorizing Tags in Tag Cloud: A Novel Query-by-Tag Music Search System	Ju-Chiang Wang*, National Taiwan University; Yu-Chin Shih, National Taiwan University; Meng-Sung Wu, ; Hsin-Min Wang, Academia Sinica; Shyh-Kang Jeng, National Taiwan University

Research 8: Media authoring and production Session Chair: Nicu Sebe, University of Trento
3D Cinematography Principles and Their Applications to Stereoscopic Media Processing	Chun-Wei Liu, ; Tz-Huan Huang, ; Ming-Hsu Chang, ; Ken-Yi Lee, National Taiwan University; Chia-Kai Liang, Lytro; Yung-Yu Chuang*, National Taiwan University
Why did the Prime Minister resign? --- Generation of event explanation from large news repositories ---	Frank Nack, UvA; Ichiro IDE*,
The DirectorÕs Lens: An Intelligent Interface for Composing Virtual 3D Cinema	Marc Christie*, IRISA / INRIA Rennes; Roberto Ranon, University of Udine; Christophe Lino, INRIA Rennes; William Bares, Millsaps College
Reliving On Demand: A Total Viewer Experience	Vivek Singh, University of Califonia at Irvine; Jiebo Luo*, Kodak; Dhiraj Joshi, Kodak; Phoury Lei, Kodak; Madirakshi Das, Kodak; Peter Stubler, Kodak

Back to Overview

---

Grand Challenge Finalists

Back to Overview

---

Poster day 2

Session Chair: Mei Tao

All papers, including short papers, long papers, workshop papers, and others, will also be presented in the poster plenary sessions on the same day as their regular presentations.

Short Papers
User-aware Image Tag Refinement via Ternary Analysis	Jitao Sang, Chinese Academy of Science; Jing Liu, ; Changsheng Xu*,
Known-Item Video Search via Query-to-Modality Mapping	Kong Wah Wan, ; Yan-tao Zheng*, ; Chaisorn Lekha,
Transfer Tagging from Image to Video	Yang Yang, The University of Queensland; Yi Yang, The University of Queensland; Helen Huang, ; Heng Tao Shen*, "The University of Queensland, Australia"
Detection of Pornographic Content in Internet Images	Srinivasan Sengamedu*, yahoo! Labs India; Subhajit Sanyal, Yahoo! Labs, India
Effective Summarization of Large-Scale Web Images	Chunlei Yang*, UNCC
Real-time Human Action Search using Random Forest based Hough Voting	Gang YU*, NANYANG TECHNOLOGICAL UNIV; Junsong Yuan, NANYANG TECHNOLOGICAL UNIVERSITY; zicheng Liu, Microsoft
Ensemble Multi-Instance Multi-Label Learning Approach for Video Annotation Task	Xin-Shun Xu*, Nanjing University
Nonparametric Bottom-Up Saliency Detection Using Hypercomplex Spectral Contrast	Ce Li*, Xi an jiaotong University
Multiclass object detection by combining local appearances and context	LiMin Wang*, Nanjing University; Yirui Wu, Nanjing University; Tong Lu, Nanjing University; Kang Chen,
Shared Feature Extraction for Semi-supervised Image Classification	Luo Yong*, Peking University; Dacheng Tao, ; Bo Geng, Peking University; Xu Chao,
Difficulty Guided Image Retrieval using Linear Multiview Embedding	Li Yangxi*, Peking university; Bo Geng, Peking University; Dacheng Tao, ; zheng-Jun Zha, ; Xu Chao,
Detection and Location of Near-Duplicate Video Sub-Clips by Finding Dense Subgraphs	Tianlong Chen*, Chinese academy of sciences; Shuqiang Jiang, ICT, CAS; lingyang Chu, ; Qingming Huang,
QUERY EXPANSION BY SPATIAL CO-OCCURRENCE FOR IMAGE RETRIEVAL	Yingfei Li*, PKU; Bo Geng, Peking University; zheng-Jun Zha, ; Li Yangxi, Peking university; Dacheng Tao, ; Xu Chao,
Social Image Tag Recommendation by Concept Matching	Aixin Sun*, Nanyang Technological University; Sourav Bhowmick, Nanyang Technological University
Automatic Image Annotation with Weakly Labeled Dataset	Wei Zhang*, Fudan University; Yao Lu, Fudan University; Xiangyang Xue, Fudan University; Jianping Fan, UNCC
Efficient Approximate Nearest Neighbor Search with Integrated Binary Codes	Wei Zhang*, ICT,CAS,China
Content Quality Based Image Retrieval With Multiple Instance Boost Ranking	Peng Yang*, Rutgers University
Detecting Motion Synchrony by Video Tubes	Ying Zheng*, DUKE UNIVERSITY; Steve Gu, Duke University; Carlo Tomasi, Duke University
Automatic Image Tagging through Information Propagation in a Query Log Based Graph Structure	Teresa Bracamonte*, University of Chile, Computer Science Department; Barbara Poblete, University of Chile, Computer Science Department
Identifying Authoritative Sources of Multimedia Content	Lyndon Kennedy*, Yahoo! Research; Malcolm Slaney, Yahoo
Semantic Point Detector	Kuiyuan Yang*, University of Science and Tech; Lei Zhang, Microsoft Research Asia; Meng Wang, ; Zhang Hong-Jiang,
Preference-Aware View Recommendation System for Cameras based on Bag of Aesthetics-Preserving Features	Hsiao-Hang Su*, National Taiwan University; Tse-Wei Chen, National Taiwan University; Chieh-Chi Kao, National Taiwan University; Winston Hsu, National Taiwan U; Shao-Yi Chien, National Taiwan University
Hybrid Image Summarization	Jingdong Wang*, Microsoft Research Asia; Xian-Sheng Hua, Microsoft
Multimodal Fusion for Video Copy Detection	Xavier Anguera Miro*, Telefonica I+D; Juan Manuel Barrios, University of Chile; Tomasz Adamek, TID; Nuria Oliver, "Telefonica, Spain"
Accurate Pedestrian Detection with Geometric Context from a Single Image	Junqiang Wang*, BUPT; Ma Huadong, ; anlong Ming,
Risk Management for Video-on-Demand Servers Leveraging Demand Forecast	Di Niu*, University of Toronto; Hong Xu, University of Toronto; Baochun Li, University of Toronto; Shuqiao Zhao, UUSee, Inc.
Prefetching Strategy in Peer-assisted Social Video Streaming	Zhi Wang*, Tsinghua University; Lifeng Sun, ; Shiqiang Yang,
Resource Allocation for Cloud-based Free Viewpoint Video on Mobile Phone	Dan Miao*, USTC; Wenwu Zhu, Microsoft Research Asia; Chang Wen Chen, SUNY at Buffalo
APRICOD: Access Pattern-Driven Content Discovery System for Nonlinear Media Access	Zhen Wei Zhao*, NUS; Wei Tsang Ooi,
Robust Image Registration and Tampering Localization Exploiting Bag of Features Based Forensic Signature	Sebastiano Battiato, University of Catania; Giovanni Farinella*, University of Catania; Enrico Messina, University of Catania; Giovanni Puglisi, University of Catania
Towards Content-based Audio Fragment Authentication	Wei Li*, Fudan University,China
Cap detection for moving people in entrance surveillance	Rui Min*, EURECOM; Jean-Luc Dugelay, EURECOM
High Efficient Distributed Video Coding with Parallelized Design for Cloud Computing	Han-Ping Cheng, National Taiwan University; Yun Chung Shen*, National Taiwan University; Ja-Ling Wu, National Taiwan University; Kiyoharu Aizawa, The University of Tokyo
Real-time Decoding for LDPC Based Distributed Video Coding	Tse-Chung Su*, National Taiwan University; Yun Chung Shen, National Taiwan University; Ja-Ling Wu, National Taiwan University
Mixing remote locations using shared screen as virtual stage	Shingo Uchihashi*, Fuji Xerox Co., Ltd.; Tsutomu Tanzawa, University of Yamanashi
On The Performance of Cloud Gaming Services	Kuan-Ta Chen*, Academia Sinica; Yu-Chun Chang, ; Po-Han Tseng, ; Chun-Ying Huang, ; Chin-Laung Lei,
Distributed Video Coding with Compressive Measurements	Hsiao-Yun Tseng*, National Taiwan University; Yun Chung Shen, National Taiwan University; Ja-Ling Wu, National Taiwan University
Personalized Portraits Ranking	Lei Huang*, ICT,CAS; Tian Xia, Institute of Computing Technology, Chinese Academy of Sciences; Ji Wan, Institute of Computing Technology, Chinese Academy of Sciences; Yongdong Zhang, ; Shouxun Lin,
A New Analysis Method for Paired Comparison and Its Application to 3D Quality Assessment	Jong-Seok Lee*, EPFL; Lutz Goldmann, EPFL; Touradj Ebrahimi, Ecole Polytechnique Federale de Lausanne
ImagiLight: an intuitive, scalable framework for lighting scene setting	Tommaso Gritti*, Philips Research; Gianluca Monaci, Philips Research
Consensus-based Cross-correlation	Florian Schweiger*, TU Muenchen; Georg Schroth, TU Muenchen; Michael Eichhorn, TU Muenchen; Eckehard Steinbach, "Munich University of Technology, Germany"; Michael Fahrmair,
Modeling Motion Visual Perception for Video Quality Assessment	Junyong You*, NTNU; Touradj Ebrahimi, Ecole Polytechnique Federale de Lausanne; Andrew Perkis, NTNU
Automatic Object Segmentation from Large Scale 3D Urban Point Clouds through Manifold Embedded Mode Seeking	Zhiding Yu*, HKUST; Chunjing Xu, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Jianzhuang Liu,
Key Object-based Static Video Summarization	Zhiqiang Tian*, Xi an JiaoTong university
Example-based Human Motion Extrapolation Based on Manifold Learning	Nick Tang*, Academia Sinica
CuteChat: A lightweight tele-immersive video chat system	Jiangbo Lu*, Advanced Digital Sciences Cent; Viet Anh Nguyen, ; Zeping Niu, ; Bhavdeep Singh, ; Zhiping Luo, ; Minh Do,
Energy-aware Complexity Adaptation for Mobile Video Calls	Haiyang Ma*, National Univ. of Singapopre; Deepak Gangadharan, National University of Singapore; Roger Zimmermann, National University of Singapore
Fast Frame-rate Up-conversion of Depth Video via Video Coding	Yanjie Li, ; Lifeng Sun*, Tsinghua University; Tianfan XUE, CUHK
Multimodal QoE Evaluation in P2P-based IPTV Systems	Mu Mu*, Lancaster University; Johnathan Ishmael, Lancaster University; Keith Mitchell, Lancaster University; Nicholas Race, Lancaster University
Blind navigation with a wearable range camera and vibrotactile helmet	Steve Mann*, University of Toronto; Ryan Janzen, University of Toronto
Recognizing Interaction Between Human Performers Using 'Key Pose Doublet'	Snehasis Mukherjee*, Indian Statistical Institute; Sujoy Kumar Biswas, Indian Statistical Institute; Dipti Prasad Mukherjee, Indian Statistical Institute
High-Efficient Software Parallel CAVLC Encoder Based on Programmable Stream Processor	Huayou Su*, NUDT
A real-time database architecture for motion capture data	Wang Pengjie, ; Rynson Lau, City University of Hong Kong; Zhang Mingmin*, State Key lab of CAG & CG, Zhe; Wang Jiang, ; Song Haiyu,
Once Upon a Time, I Bought a Movie and It Played Everywhere in My Home	Jay Geagan, IBM Almaden Research Center; Dulce Ponceleon, IBM Almaden Research Center

Back to Overview

---

Doctoral Symposium 1: Panel - Career Perspective and Job Opportunities for Graduates of the Multimedia Community
 

Wednesday, Nov. 30, 2011, 2:00 PM - 3:30 PM

This NSF funded event aims to create a forum where students who are interested in and dedicated to multimedia research can learn career perspective and job opportunities from the senior researchers. A number of senior researchers from both industry and academia have been confirmed as speakers/discussants for this panel, including (in alphabetical order by the surname):

K. Selcuk Candan
Professor
School of CIDSE, Arizona State University
candan@asu.edu

K. Selcuk Candan is a Professor of Computer Science and Engineering at the School of Computing, Informatics, and Decision Science Engineering at the Arizona State University and is leading the EmitLab research group. He joined the department in August 1997, after receiving his Ph.D. from the Computer Science Department at the University of Maryland at College Park. Prof. Candan's primary research interest is in the area of management of non-traditional, heterogeneous, and imprecise (in particular, multimedia, web, and scientific) data. His various research projects in this domain are funded by diverse sources, including the National Science Foundation, Department of Defense, Mellon Foundation, and various in- dustrial research labs. He has published over 150 articles and many book chapters. He has also authored 9 patents. Recently, he co-authored a book titled \Data Management for Multimedia Retrieval" for the Cambridge University Press and co-edited \New Frontiers in Information and Software as Services: Service and Application Design Challenges in the Cloud" for Springer.

Recently, Prof. Candan served as an editorial board member of the Very Large Databases (VLDB) journal and the Journal of Multimedia. He has served in the organization and program committees of various conferences. In 2006, he served as an organization committee member for SIGMOD'06, the flagship database conference of the ACM and one of the best conferences in the area of management of data. In 2008, he served as a PC Chair for another leading, flagship conference of the ACM, this time focusing on multimedia research (MM'08). He also served in the review board of the Proceedings of the VLDB Endowment (PVLDB). In 2010, he was a program co-chair for ACM CIVR'10 conference and a program group leader for ACM SIGMOD'10. In 2011, he is serving as a general co-chair for the ACM MM'11 conference and is in the executive committee of ACM SIGMM. In 2012, he will serve as a general co-chair for ACM SIGMOD'12. In 2012, he will also serve in the organizing committees of ACM MM'12 and VLDB'12.

Lyndon Kennedy
Scientist
Yahoo! Research
lyndonk@yahoo-inc.com

Lyndon Kennedy is a scientist at Yahoo! Labs in Santa Clara, CA, where he investigates techniques for automatically indexing, searching, and managing digital image and video collections. He received a Ph.D. degree in 2009 in Electrical Engineering from Columbia University, where he conducted research in the Digital Video and Multimedia Lab under the direction of Prof. Shih-Fu Chang. He also holds B.S. (2003) and M.S. (2005) degrees, both in EE from Columbia University.

His research has received several awards and honors. He was co-author of a paper awarded the IBM Student Paper Award at ICIP in 2004. In 2006 and 2009, he was co-author of papers nominated for the Best Paper awards at ACM Multimedia and the ACM Workshop on Social Media, respectively. In 2007, he was invited as part of a group of 8 top senior Ph.D. students in the multimedia ¯eld to participate in the IBM Watson Emerging Leaders in Multimedia Workshop.

Dulce Ponceleón
Research Staff Member
IBM Almaden
dulce@almaden.ibm.com

Dr. Dulce Ponceleón is a Research Sta® Member at IBM Research - Almaden since 1997, where she currently manages the Content Protection Group. Last year she was a recipient of the 26th Annual Tribute toWomen (TWIN) Awards given by the YWCA of Silicon Valley in recognition of women who demonstrate excellence in industry. She is a technical contributor and IBM representative to the content protection standards for Blu-ray, i.e. Advanced Access Content System (www.aacsla.com) and the Technical Chair of 4C (www.4centity.com), a content protection standards for recordable and pre-recorded media. Shs is a key contributor to 4C's specifications for Secure Digital cards applications. She is IBMSs Research Relationship Manager (RRM) for Media & Entertainment. In this role she brings the industry requirements to IBM' research labs world-wide and promotes partnership with other IBM organizations to strengthen and differentiate IBM' s offerings. While at IBM she conducted research in multimedia, from multimedia analysis and retrieval to audio and video compression, video summarization, content protection and multimedia security. Previously, she worked at Apple Computer, Inc. where she was a key contributor to the first video& audio codec supported by Apple's QuickTime Conferencing, the first software-only videoconferencing system. She received her M.S. and Ph.D. degrees in computer science from Stanford University. She is the author of numerous publications, 19 patents, and a chapter in the text book Modern Information Retrieval: The Concepts and Technology behind Search (2nd Edition). Dr. Poncelelon has served in numerous program committees and held workshops, tutorials, and panels in the areas of multimedia and security.

Hari Sundaram
Associate Professor
Arts Media and Engineering, Arizona State University
hari.sundaram@asu.edu

Hari Sundaram is currently an associate professor of media arts and computing, with the School of Arts Media and Engineering, and Computer Science at Arizona State University. He received his Ph.D. from the Department of Electrical Engineering at Columbia University in 2002. He is interested in understanding human activity in physical spaces, as well as in online social networks. In the former, he has investigated the design of immersive multimedia environments for stroke patient rehabilitation. Another way to think about this work: can we design machines to teach human beings specific physical skills that enable them to perform functional tasks? His work on social networks has focused on several broad themes: discovering communities, analyzing communication patterns, behavioral cascades, and design of social games for motivating work. We can use results from the work on community discovery, as an example, several scenarios: sparking innovation in conferences, creating cooperative behavioral cascades as well as in more meaningful information search. His research has won several awards (the best student paper award at JCDL 2007, the best ACM Multimedia demo award in 2006). He received the best student paper award at ACM Multimedia 2002, and the Eliahu I. Jury Award for best Ph.D. dissertation in 2002. He also received in 2000, a best paper award on video retrieval from IEEE Trans. On Circuits and Systems for Video Technology. He is an active participant in the Multimedia community; he is an associate editor at several major journals: ACM Transactions on Multimedia Computing, Communications and Applications (TOMCCAP), IEEE Multimedia and IEEE Transactions on Multimedia. He will co-organize the upcoming ACM SIG Multimedia 2011.

Rong Yan
Research Scientist
Facebook
rongyan@fb.com

Dr. Rong Yan is currently a Research Scientist in Facebook. He was a Research Sta® Member in the IBM T. J. Watson Research Center from 2006 to 2009. Dr. Yan received his M.Sc. (2004) and Ph.D. (2006) degree from Carnegie Mellon University's School of Computer Science.

His research interests include digital and social media analysis, large-scale machine learning, data mining, information retrieval and computer vision. Dr. Yan received the BestPaper runner-up awards in ACM MM 2004 and ACM CIVR 2007. He led the technical e®orts for building Facebook's face detection / recognition service, and designed the automatic video retrieval systems that achieve the best performance in the world-wide TRECVID evaluation in 2003 / 2005. He has received the IBM Research External Recognition Award in 2007. Dr. Yan has authored or co-authored 5 book chapters and more than 60 international conference and journal papers. He has served or is serving as co-chairs for 10 conferences / workshops and as a Program Committee member in more than 40 ACM / IEEE conferences. He gave tutorials and guest lectures at several major conferences and universities.

Roger Zimmerman
Associate Professor
Dept. of Computer Science, National University of Singapore
rogerz@comp.nus.edu.sg

Roger Zimmermann is an Associate Professor with the Department of Computer Science at the National University of Singapore (NUS) where he is also an investigator with the Interactive and Digital Media Institute (IDMI). Prior to joining NUS he held the position of Research Area Director with the Integrated Media Systems Center (IMSC) at the University of Southern California (USC). He received his Ph.D. degree from USC in 1998. Among his research interests are distributed and peer-to-peer systems, collaborative environments, streaming media architectures, georeferenced video management, and mobile location-based services. He has co-authored a book, five patents and more than a hundred-twenty conference publications, journal articles and book chapters in the areas of multimedia and information management. He is an Associate Editor of the ACM Computers in Entertainment magazine and the ACM Transactions on Multimedia Computing, Communications and Applications journal. He is a Senior Member of the IEEE and a member of ACM

Back to Overview

---

Doctoral Symposium 2: Poster Session

Wednesday, Nov. 30, 2011, 3:30 PM - 4:45 PM

Poster set-up begins at 12:30 PM. Refreshments will be served during poster session.

Posters
From wide-baseline unordered images to path videos	Aveek Shankar Brahmachari	abrahmac@mail.usf.edu
RAYS: Recall All You See	Sumita Barahmand	barahman@usc.edu
Modeling Tagged Photos for Automatic Image Annotation	Neela Sawant	nks125@ist.psu.edu
Using Ephemeral Clustering and User Feedback to Improve Image Retrieval for Mobile Devices	Jose G. Moreno	jose.moreno@unicaen.fr
Multimedia Information Retrieval in the Social Web	Teresa Bracamonte	tbracamo@dcc.uchile.cl
Video Concept Detection using web-based Training Sources	Damian Borth	damian.borth@dfki.de
CloudTracker: Accelerating Internet Content Distribution by Bridging Cloud Servers and Peer Swarms	Zhenhua Li	lizhenhua1983@gmail.com
Conformal Geometry Videos	Dao Thi Phuong Quynh	daot0006@ntu.edu.sg
Objects Detection and Recognition for People with Visual Impairment	Xiaodong Yang	yangxd.hust@gmail.com
Music Genre Classification Using Explicit Semantic Analysis	Kamelia Aryafar	kca26@drexel.edu
Dynamic Batch Mode Active Learning	Shayok Chakraborty	schakr10@asu.edu
Intelligent Query Formulation for Mobile Visual Search	Felix X. Yu	yuxinnan@ee.columbia.edu
Methods for Sensor-rich Video Management (GeoVid)	Zhijie Shen	z-shen@comp.nus.edu.sg
Indexing and Visualization of Presentation Videos	Michele Merler	mmerler@cs.columbia.edu
The Building Blocks of Touch-Based Information Delivery	Troy McDaniel	troy.mcdaniel@asu.edu
Bilinear deep learning for image classification	Sheng-hua Zhong	csshzhong@comp.polyu.edu.hk
Building Low-Latency Remote Rendering Systems for Interactive 3D Graphics Rendering on Mobile Devices	Shu Shi	shushi2@illinois.edu
Image Search 2.0	Xirong Li	x.li@uva.nl
Beyond Video Searching: Large-scale Web Video Exploration	Song TAN	songtan@student.cityu.edu.hk
Acropolis: An Operating System for Real-Time Multistreaming Systems	Raoul Rivas	raoul1024@gmail.com
Towards Efficient Resource Utilization in Internet Mobile Streaming	Yao Liu	yliud@cs.gmu.edu
Multiple Object Retrieval in Image Databases Using Hierarchical Segmentation Tree	Wei-Bang Chen	wbc0522@uab.edu
A Multimodality Approach towards Video Genre Detection	Richa Tiwari	rtiwari@uab.edu
Robust Image Representation for Efficient Recognition and Retrieval	Xia Li	xial@cs.utsa.edu
Seeing' ENF: Natural Time Stamp for Digital Video via Optical Sensing and Signal Processing	Ravi Garg	ravig@umd.edu
Real-Time Customizable Sound Design Toolkit	Diana Siwiak	dsiwiak@asu.edu
Human-centric Approaches in 3D Tele-Immersive Systems	Wanmin Wu	wanmin.wu@gmail.com
From Multimedia Data to Situations	Vivek K. Singh	singhv@uci.edu

Back to Overview

---

Doctoral Symposium 3: Oral Presentations
 

Wednesday, Nov. 30, 2011, 4:45 PM - 6:00 PM

Oral Presentations
From Local Features to Local Regions	Romberg, Stefan	stefan.romberg@informatik.uni-augsburg.de
Synchronized Dissemination Framework for Supporting High-Quality Tele-Immersive Shared Activity	Huang, Zixia	zhuang21@illinois.edu
Learning-based Real-time Universal Session Monitoring and Management Framework for Correlated Multi-stream 3D Tele-immersive Environments	Arefin, Md	marefin2@illinois.edu
Local Features for Partial Shape Matching and Retrieval	Sipiran, Ivan	isipiran@dcc.uchile.cl

Back to Overview

---

J-MRE

Joint ACM Workshop on Modeling and Representing Events (J-MRE'11)
Wednesday Nov. 30, 2011
Part 1: International ACM Workshop on Events in Multimedia (EiMM11)
Ansgar Scherp (University of Koblenz-Landau, Germany)
Ramesh Jain (University of California at Irvine (UCI))
Mohan S. Kankanhalli (National Univ. of ingapore)
Vasileios Mezaris (Centre for Research and Technology Hellas, Greece)
Part 2: International ACM Workshop on Sparse Representationfor Event Detection in Multimedia (SRED’11)
Huiyu Zhou (Queen’s University Belfast, United Kingdom)
Jianguo Zhang (University of Dundee, United Kingdom)
Liang Wang (National Lab of Pattern Recognition, Beijing, China)
Zhengyou Zhang (Microsoft Research, Microsoft Corp., One Microsoft Way, Redmond WA, USA)

Session Schedule:

Paper ID No. (see the chairsview of the Sheridan/ACM submission system for the  submission ID#s)	Title of Accepted Paper, Poster, Panel, Abstract, Invited Talk  or Keynote	For Sheridan Printing Use
	Front Matter (Copyright Page – Sheridan Printing will create this page for the conference chairs) (Table of Contents —Sheridan Printing will create the Table of Contents (& Author Index) from the updated information the authors enter on the submission page with their final versions) (Organization Pages, Please see the Sheridan Printing supplied sample files and be sure you (the chairs) have included all the chairs, committees, and organizers).
Session 1	Event detection from multimedia content
	Session Chair: Vasileios Mezaris (Centre for Research and Technology Hellas, Greece)
10:30	Event Detection and Scene Attraction by Very Simple Contextual Cues - Ivan Tankoyeu (University of Trento, IT); Javier Paniagua (University of Trento, IT); Julian Stöttinger (University of Trento, IT); Fausto Giunchiglia (University of Trento, IT)
11:00	Exploitation of time constrains for (sub-)event Recognition - Riccardo Mattivi (University of Trento, IT); Jasper Uijlings (University of Trento, IT); Francesco De Natale (University of Trento, IT); Nicu Sebe (University of Trento, IT)
11:30	Trajectories based descriptor for dynamic events annotation - Nicolas Ballas (CEA-LIST, FR); Betrand Delezoide (CEA-LIST, FR)
12:00	Acoustic Super Models for Large Scale Video Event Detection - Robert Mertens (ICSI, USA); Howard Lei  (ICSI, USA); Luke Gottlieb (ICSI, USA); Gerald Friedland (ICSI, USA); Ajay Divakarian (Sarnoff/SRI International, USA)
Session 2	Sparse representation and event-based applications
	Session Chair: Ansgar Scherp (University of Koblenz, Germany)
2:00	Dynamic Texture Reconstruction from Sparse Codes for Unusual Event Detection in Crowded Scenes - Jingxin Xu (QUT, AU); Simon Denman (QUT, AU); Sridha Sridaran (QUT, AU); Clinton Fookes (QUT, AU); Rajib Rana (QUT, AU)
2:30	Sequence-Kernel Based Sparse Representation for Amateur Video Summarization - Zheshen Wang (Arizona State University, USA); Mrityunjay Kumar (Eastman Kodak Company, USA); Jiebo Luo (Eastman Kodak Company, USA); Baoxin Li (Arizona State University, USA)
3:00	Finding the Game Flow from Sports Video - Yi Ding (Oklahoma State University, USA); Guoliang Fan (Oklahoma State University, USA)
3:30	Lifelog Event Management: Crowd Research Case Study - Pil Ho Kim (University of Trento, IT); Fausto Giunchiglia (University of Trento, IT)
Keynote	Keynote Address
	Session Chair: Ansgar Scherp (University of Koblenz, Germany)
4:30	Event and story - an intricate relationship - Frank Nack (University of Amsterdam, NL)
	AUTHOR INDEX—Sheridan Printing will generate and create the author index from the submission system and the authors final versions for either print, eproceedings, or both.

Back to Overview

---

WSM

International ACM Workshop on Social Media (WSM11)
Wednesday Nov. 30, 2011
Michal Jacovi (IBM Haifa Research Lab, Israel)
Steven C.H. Hoi (Nanyang Technological University, Singapore)
Yiannis Kompatsiaris (Informatics and Telematics Institute, Greece)
Jiebo Luo (Kodak Research Labs, USA)
Konstantinos Tserpes (Harokopio University of Athens, Greece)

Session Schedule:

Welcome and Keynote 1	Session Chair: Prof. Jiebo Luo (Rochester University)
10:30 – 10:35	Welcome
10:35 – 11:25	Mining Social Media - Issues and Challenges, Prof. Huan Liu, Arizona State University
Session 1	Information Extraction and Content Organization Session Chair: Dr. Yiannis Kompatsiaris (CERTH – Informatics and Telematics Institute)
11:25 – 11:50	Using social media to identify events Raphael Troncy; Benoit Huet; Xueliang Liu
11:50 – 12:15	Sentiment analysis of social media content using n-gram graphs Georgios Papadakis; Fotis Aisopos; Theodora Varvarigou
12:15 – 12:40	Laplacian adaptive context-based svm for incremental video concept detection Wei Jiang; Alexander Loui
12:40 – 14:00	Lunch
Session 2	Location-based approaches Session Chair: Konstantinos Tserpes (Harokopio University of Athens, Greece)
14:00 – 14:25	Multimodal location estimation on flickr videos Gerald Friedland; Jaeyoung Choi; Howard Lei; Adam Janin
14:25 – 14:50	IM2MAP: Deriving maps from georeferenced community contributed photo collections Shawn N; Ling Xie
14:50 – 15:15	Tag suggestion and localization for web videos by bipartite graph matching Wei-Ta Chu; Cheng-Jung Li; Jen-Yu Yu
Keynote 2	Keynote Address Session Chair: Steven C. H. Hoi (Nanyang Technological University, Singapore)
15:15 – 16:05	Large-scale Social Media Analysis in Facebook, Dr. Rong Yan, Facebook Inc.
16:05 – 16:30	Coffee Break
Session 3	Social Media Applications and Studies Session Chair: Roelof van Zwol (Yahoo! Research, USA)
16:30 – 16:55	Photo stream alignment for collaborative photo collection and sharing in social media Jianchao Yang; Jiebo Luo
16:55 – 17:20	Near2me: An authentic and personalized social media-based recommender for travel destinations Christoph Kofler; Maria Luz Caballero; Maria Menendez Blanco; Valentina Occhialini; Martha Larson
17:20 – 17:45	Why do we converse on social media? an analysis of intrinsic and extrinsic network factors. Munmun De Choudhury; Hari Sundaram
18:45 – 18:10	Chase display of social live streams (soliss) Sumita Barahmand; Shahram Ghandeharizadeh
18:10 – 18:30	Discussion and Closing

Back to Overview

---

MIRUM

International ACM Workshop on Music Information Retrieval with User-Centered and Multimodal Strategies (MIRUM'11)
Wednesday Nov. 30, 2011
Cynthia Liem (Delft University of Technology, Netherlands)
Douglas Eck (Google Inc., USA)
Meinard Müller (Saarland University/MPI für Informatik, Germany)
George Tzanetakis (University of Victoria, Canada)

Session Schedule
Session 1: 10:30-12:30, Session chair: Xavier Anguera Miro, Telefonica R&D, Spain
10:30 - 10:55	OPENING REMARKS AND INTRODUCTION - The Need for Music Information Retrieval with User-Centered and Multimodal Strategies	Cynthia Liem,  Meinard Müller;  Douglas Eck; George Tzanetakis; Alan Hanjalic
10:55 - 11:20	Affective Content Analysis of Music Video Clips	Ashkan Yazdani; Krista Kappeler; Touradj Ebrahimi
11:20 - 11:40	A Tempo-Sensitive Music Search Engine With Multimodal Inputs	Yu Yi; Yinsheng Zhou; Ye Wang
11:40 - 12:30	KEYNOTE - Audiovisual Archive Exploitation in the Networked Information Society	Roeland Ordelman
12:30-2:00, LUNCH BREAK AND PLENARY POSTER SESSION Posters of MIRUM workshop papers will be presented alongside regular and short papers of the main conference
Session 2: 2:00-4:00, Session chair: Gaël Richard, Telecom ParisTech, France
2:00 - 2:25	Music Identification via Vocabulary Tree with MFCC Peaks	Tianjing Xu; Wei Yu; Xianglong Liu
2:25 - 2:50	Finding Geographically Representative Music via Social Media	Charles Parker; Dhiraj Joshi; Phoury Lei; Jiebo Luo
2:50 - 3:15	Music Genre Classification using Explicit Semantic Analysis	Kamelia Aryafar; Ali Shokoufandeh
3:15 - 4:00	PANEL - Bridging opportunities for the music and multimedia domains	Moderator: Cynthia Liem (Delft University of Technology, The Netherlands) Panelists: Ye Wang (National University of Singapore, Singapore), Jean Bresson (IRCAM, France), Alan Hanjalic (Delft University of Technology, The Netherlands), Gerald Friedland (University of California, Berkeley, USA)
Session 3: 4:30-6:30, Session chair: Ju-Chiang Wang, National Taiwan University, Taiwan
4:30 - 4:55	Analyzing Sound Tracings - A Multimodal Approach to Music Information Retrieval	Kristian Nymoen; Baptiste Caramiaux; Mariusz Kozak; Jim Torresen
4:55 - 5:20	Advantages of nonstationary Gabor transforms in beat tracking	Andre Holzapfel; Arthur Flexer; Monika Dorfler; Gino Velasco; Nicki Holighaus
5:20 - 5:45	A Musical Mood Trajectory Estimation Method Using Lyrics and Acoustic Features	Naoki Nishikawa; Katsutoshi Itoyama; Hiromasa Fujihara; Masataka Goto; Tetsuya Ogata; Hiroshi G. Okuno
5:45 - 6:10	What is a 'musical world'? An affinity propagation approach	Eugenio Tacchini; Ernesto Damiani
6:10 - 6:30, CLOSING REMARKS

Back to Overview

---

Networking of Multimedia Women Event
Beyond Epsilon Science
“Where to look and How to realize new opportunities”

“Networking of Multimedia Women” event is a continuation of an on-going conversation in the multimedia research community and efforts by the ACM SIGMM to engage and promote female researchers in multimedia community, enable networking of  junior and senior female researchers, and give insights towards successful professional careers based on examples.

This year, the event will have a theme, called “Beyond Epsilon Science”, where preeminent senior female researchers from academia, industry and government will present and discuss how to go beyond epsilon science, where to look for big ideas with high social impact, as well as how to obtain funding to realize these ideas, innovations and opportunities. Their current research projects and funding efforts, and their personal experiences will drive the event‘s discussions, awareness of major research and funding initiatives, answers to open questions and insights into successful professional careers.

Download  Download Slides of Panel on Networking of Multimedia Women.

Event Chair: Klara Nahrstedt, University of Illinois at Urbana-Champaign

Agenda:

November 30, 2011., 10:30-11:00                 Talk 1
Title:  “When was the last time your project made you smile?: Doing Computer Science that builds Social Capital”, 
Speaker: Svetha Venkatesh, Curtin University, Australia

Abstract: In this talk, Professor Ventakesh describes her close encounters in pursuit of early intervention technology for children with Autism Spectrum Disorder. ASD affects 1 in 150 children at an estimated cost of $3.2 million per sufferer, a figure that pales beside the cost to sufferers and parents in anxiety, anger, stress, and depression. Fast and reliable early intervention is critical, but current approaches are laborious and costly, and waiting lists are long. In response, she has partnered with Autism West and psychologists at the cutting edge of therapy to build early intervention software based on evidence-based learning theory that delivers stimulus of increasing complexity and adapts to learner performance. She shows why it changes the landscape of early intervention, and demonstrates the first iPad-based Waitlist program. She describes her journey, its challenges and when it made her smile.

Bio: Dr. Svetha Venkatesh holds the Inaugural John Curtin Distinguished Professorship. Venkatesh was elected a Fellow of the International Association of Pattern Recognition in 2004 for contributions to formulation and extraction of semantics in multimedia data. She is a Fellow of the Australian Academy of Technological Sciences and Engineering. She is on the editorial board of the both premier multimedia journals: IEEE Transactions on Multimedia and ACM Transactions on Multimedia, and a program member of several international conferences such as ACM Multimedia. Venkatesh has developed frontier technologies in large scale pattern recognition exemplified through 346 publications including 2 books, 12 book chapters, 78 journal and 254 conference publications. She has won over $12.1 million in competitive research funding since 1992. Venkatesh and her colleagues have filed 9 patents, of which 3 are full patents. One start-up company, spun out of these patents is Virtual Observer and based on the paradigm shifting methods that leverages mobile cameras to deliver wide area surveillance solutions. The technology won the Runner up in both the WA Inventor of the year (Early stage) and Global Security Challenge (Asia-Pacific) in 2007. A recent spin-out company is iCetana and is based on novel methods to find anomalies in video data. iCetana won the Broadband Innovation Award at the prestigious Tech23 in 2010.

November 30, 2011, 11:00-11:30                   Talk 2
Title: “Multimodal Situational Awareness for Societal-scale Emergency Response”,
Speaker: Nalini Venkatasubramanian, University of California, Irvine, USA.

Abstract: In this talk, Professor Venkatasubramanianshows how technology and research can help save lives and property by responding effectively to natural and manmade disasters. Situational information is critical in disasters –effective response relies on extracting actionable awareness from multiple sources in crises.  Multimedia information sources provide rich content (e.g. speech, audio, images, video, text, social media) regarding the evolving state of the disaster – this information is vital for creating awareness that leads to improved decision making and response.  She will describe her research experiences in developing and deploying multimodal situational awareness technologies for emergency response. She will highlight key fundamental scientific research problems and solution strategies for the collection/dissemination of situational content and walk through the process of translating this to validation and deployment of real world system artifacts for the emergency response community.  This work opens up new possibilities for the design of resilient, adaptive and scalable societal scale systems of the future.

Bio: Dr. Nalini Venkatasubramanian  is currently a Professor in the School of Information and Computer Science at the University of California Irvine. She has had significant research and industry experience in the areas of distributed systems, adaptive middleware, pervasive and mobile computing, distributed multimedia and formal methods and has published extensively in these areas. As a key member of the Center for Emergency Response Technologies at UC Irvine, Nalini's recent research has focused on enabling resilient, scalable observation and analysis of situational information from multimodal input sources, techniques for dynamic adaptation of the underlying systems to enable information flow under massive failures and the dissemination of rich notifications to members of the public at large.  Many of her research contributions have been incorporated into software artifacts which are now in use at various first responder partner sites. She is the recipient of the prestigious NSF Career Award, an Undergraduate Teaching Excellence Award from the University of California, Irvine in 2002 and multiple best paper awards. Prof. Venkatasubramanian has served in numerous program and organizing committees of conferences on middleware, distributed systems and multimedia and on the editorial boards of journals. She received her M.S and Ph.D in Computer Science from the University of Illinois in Urbana-Champaign. Prior to arriving at UC Irvine, Nalini was a Research Staff Member at the Hewlett-Packard Laboratories in Palo Alto, California.

November 30, 2011, 11:30-12:30                   Panel and Discussion

Title: “Beyond Epsilon Science – Where to look and How to realize new opportunities”

Panelists: Dulce B. Ponceleon, IBM Research - Almaden, USA; Susanne Boll, University of Oldenburg, Germany; Maria Zemankova, National Science Foundation, USA; Genevieve Bell, Intel Labs, Intel.
Moderator: Klara Nahrstedt, University of Illinois at Urbana-Champaign, USA

Bio: Dr. Dulce Ponceleon is a Research Staff Member at IBM Research - Almaden since 1997, where she currently manages the Content Protection Group. Last year she was a recipient of the 26^th Annual Tribute to Women (TWIN) Awards given by the YWCA of Silicon Valley in recognition of women who demonstrate excellence in industry. She is a technical contributor to the content protection standards for Blu-ray, i.e. Advanced Access Content System (www.aacsla.com) and the Technical Chair of 4C (www.4centity.com), a content protection standards for recordable and pre-recorded media. She is a key contributor to 4C’s specifications for Secure Digital cards applications. She is IBM’s Research Relationship Manager (RRM) for Media & Entertainment. In this role she brings the industry requirements to IBM’ research labs world-wide and promotes partnership with other IBM organizations to strengthen and differentiate IBM’s offerings. While at IBM she conducted research in multimedia, from multimedia analysis and retrieval to audio and video compression, video summarization, content protection and multimedia security. Previously, she worked at Apple Computer, Inc. where she was a key contributor to the first video & audio codec supported by Apple’s QuickTime Conferencing, the first software-only videoconferencing system. Dr. Ponceleon has served in numerous program committees and held workshops, tutorials, and panels in the areas of multimedia and security. She is the author of numerous publications, 19 patents, and a chapter in the text book Modern Information Retrieval: The Concepts and Technology behind Search (2nd Edition). She received her M.S. and Ph.D. degrees in computer science from Stanford University. Last but not least she has a passion for mentoring and volunteering to encourage minorities to pursue technical careers.

Bio: Dr. Susanne Boll is Professor for Media Informatics and Multimedia Systems as Department of Computing Science at the University of Oldenburg, Germany. Also since 2002 she is a member of executive board of the OFFIS Institute for Information Technology (OFFIS) where she is scientific head of many international and national research projects in the field of semantic retrieval and intelligent user interfaces. She is leading the Human-Machine-Interaction Technology Cluster. In 2001, Susanne Boll received her doctorate with distinction at the Technical University of Vienna, Austria and her diploma degree with distinction in computer science at the Technical University of Darmstadt, Germany, in 1996.
Susanne Boll’s research interests lie in the field of semantic retrieval of digital media, context-aware and location-based mobile systems, and intelligent user interfaces. She is member of the editorial board of the IEEE Multimedia Magazine and Associate Editor of the ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMCCAP) and Springer Multimedia Tools and Applications (MTAP). As an active member of the community, Susanne served on program committees for many international conferences and also co-organized several international events. Dr. Boll is an active member of SIGMM of the ACM and GI, and also a member of IEEE Computer Society.

Bio: Dr. Maria Zemankova joined the National Science Foundation (www.nsf.gov ) as a Program Director in the Information and Intelligent Systems (IIS) Division in 1988. She has been instrumental in developing initiatives on Scientific Databases, Digital Libraries, and Biodiversity and Ecosystem Informatics, and is currently involved in Information Integration & Informatics Program, Graphics & Visualization, Graduate STEM Fellows in K-12 Education (GK-12) Program and various cross-disciplinary initiatives. Maria likes to "re-new" herself from time-to-time. She spent a year (1993 - 1994) with The MITRE Corporation and a year (2000 - 2001) at the National Library of Medicine, NIH. She is Co-Editor-in-Chief of the Journal of Intelligent Information Systems (http://www.springerlink.com/content/1573-7675/ ), a member of ACM, AAAI, IEEE, Sigma Xi, and in 1992, she received the ACM SIGMOD Contributions Award.

Bio: Dr. Klara Nahrstedt is a professor at the University of Illinois at Urbana-Champaign, Computer Science Department.   Her research interests are directed towards tele-immersive systems, Quality of Service (QoS) management in wired and wireless networks, and distributed, and pervasive mobile systems. She is the coauthor of the widely used multimedia books `Multimedia: Computing, Communications and Applications' published by Prentice Hall, and ‘Multimedia Systems’ published by Springer Verlag. She is the recipient of the Early NSF Career Award, the Junior Xerox Award, the IEEE Communication Society Leonard Abraham Award for Research Achievements, the University Scholar Award, the Humboldt Research Award, and the Ralph and Catherine Fisher Professorship Chair. She was the editor-in-chief of ACM/Springer Multimedia Systems Journal, she was the general co-chair of ACM Multimedia 2006, the general chair of ACM NOSSDAV 2007, the general chair of IEEE Pervasive Computing and Communications (Percom) 2009. Currently, she is the associate editor of ACM Transactions on Multimedia Computing, Communications and Applications, and she is the elected chair of ACM Special Interest Group in Multimedia (2007-2013). Klara Nahrstedt received her Diploma degree in mathematics and numerical analysis from Humboldt University, Berlin, in 1985. She was a research scientist in the Institute for Informatik in Berlin until 1989. In 1995 she received her PhD from the University of Pennsylvania in the Department of Computer and Information Science. She is the member of ACM and IEEE Fellow.

Back to Overview

---

Panel 2: Towards Synergy Between the Open Source and the Research Multimedia Communities

Organizers
Wei-Tsang Ooi & Pablo Cesar

Panelists
Ben Moskowitz, OVC & Mozilla Foundation, Canada
Zohar Babin, Kaltura, USA
Dick Bulterman, CWI & Vrije Universiteit, Netherlands
Rainer Lienhart, University of Augsburg, Germany
Robert Richter, Mozilla Foundation, USA
Mathias Lux, Klagenfurt University, Austria

Back to Overview