Conference Program

The program for the conference is also available in .pdf and .docx formats.

Monday March 29, 2010

Registration: 8:00AM - 8:30AM

The registration desk will also be open throughout the event.

Opening and Academic Keynote: 8:30AM - 10:00AM

Coffee break 10:00AM - 10:20AM

Oral Session 1: 10:20AM - 12:00PM Multimedia Analysis
Chair: Nuria Oliver Ramirez (Telefonica R&D, Spain)

  1. Object category recognition using multi-scale affine kernels, Tanveer Syeda-Mahmood (IBM Almaden Research Center, USA), Fei Wang (IBM Almaden Research Center, USA), David Beymer (IBM Almaden Research Center, USA)
  2. Relevance Filtering meets Active Learning: Improving Web-based Concept Detectors, Damian Borth, (University of Kaiserslautern, Germany), Adrian Ulges (DFKI, Germany), Thomas Breuel (University of Kaiserslautern, Germany)
  3. Performance Measures for Multilabel Evaluation: A Case Study in the Area of Image Classification, Stefanie Nowak (Fraunhofer Institute for Digital Media Technology, Germany), Hanna Lukashevich (Fraunhofer Institute for Digital Media Technology, Germany), Peter Dunker (Fraunhofer Institute for Digital Media Technology, Germany)
  4. Video Retargeting with Multi-scale Trajectory Optimization, Yuanning Li (Peking University, China), Yonghong Tian (Peking University, China), Jingjing Yang (Chinese Academy of Sciences, China), Lingyu Duan (Peking University, China), Wen Gao (Peking University, China)
  5. Exploring Automatic Music Annotation with "Acoustically-Objective" Tags, Derek Tingle (Swarthmore College, USA), Youngmoo Kim (Drexel University, USA), Douglas Turnbull (Swarthmore College, USA)

Lunch break 12:00PM - 1:00PM

Mini Poster and Demo Introduction Session I: 1:00PM - 1:20PM (each talk is limited to one slide for about 1 minutes; 15 talks total)
Chair: Behzad Shahraray (AT&T Labs, USA)

Special Oral Session 1: 1:20PM - 3:20PM Medical Multimedia Retrieval
Chair: Yu Cao (California State University at Fresno, USA), Henning Müller (University and University Hospitals of Geneva, Switzerland)

  1. A Classification-Driven Similarity Matching Framework for Retrieval of Biomedical Images, Md Mahmudur Rahman (National Institute of Health, USA), Sameer K. Antani (National Institute of Health, USA), George R. Thoma (National Institute of Health, USA)
  2. Chest X-ray Characterization: From the Organ identification to the Pathology categorization, Uri Avni (Tel-Aviv University, Israel), Jacob Goldberger (Bar-llan University, Israel), Michal Sharon (Sheba Medical Center, Israel), Eli Konen (Sheba Medical Center, Israel), Hayit Greenspan (Tel-Aviv University, Israel)
  3. Multimodal Medical Image Retrieval - Image Categorization to Improve Search Precision, Jayashree Kalpathy-Cramer (Oregon Health and Science University, USA), William Hersh (Oregon Health and Science University, USA)
  4. Redundancy redundancy redundancy--the key to robust medical image tagging and retrieval, Xiang Sean Zhou (Siemens Healthcare, USA), Zhigang Peng (Siemens Healthcare, USA), Yiqiang Zhan (Siemens Healthcare, USA), Maneesh Dewan (Siemens Healthcare, USA), Bing Jian (Siemens Healthcare, USA), Arun Krishnan (Siemens Healthcare, USA), Yimo Tao (Siemens Healthcare, USA), Stefan Grosskopf (Siemens Healthcare, Germany), Martin Harder (Siemens Healthcare, Germany)
  5. An Investigation into the Relationship between Semantic-based and Content-based Similarity using LIDC, Robert Kim (Johns Hopkins University, USA), Grace Dasovich (Northwestern University, USA), Runa Bhaumik (DePaul University, USA), Richard Brock (DePaul University, USA), Jacob Furst (DePaul University, USA), Daniela S. Raicu (DePaul University, USA)
  6. Augmenting Clinical Observations with Visual Features from Longitudinal MRI Data for Improved Dementia Diagnosis, Devrim Unay (Bahcesehir University, Turkey)

Poster/Demo Session and Coffee Break (John C. Bogle Chairman's Room, 3:20PM - 5:00PM)
Chair: Behzad Shahraray (AT&T Labs, USA)
Note: The poster/demo room can only hold 75 people at a time.

A. Posters:

  1. Topic Models for Semantics-preserving Video Compression, Joern Wanke (University of Kaiserslautern, Germany), Adrian Ulges (German Research Center for Artificial Intelligence, Germany), Christoph Lampert (Max Planck Institute for Biological Cybergenetics, Germany), Thomas Breuel (University of Kaiserslautern, Germany)
  2. Learning to Rank for Content-Based Image Retrieval, Fábio Augusto Faria (University of Campinas, Brazil), Adriano Veloso (Federal University of Minas Gerais, Brazil), Humberto M. Almeida (Federal University of Minas Gerais, Brazil), Eduardo Valle (University of Campinas, Brazil), Ricardo da S. Torres (University of Campinas, Brazil), Marcos A. Golçalves (Federal University of Minas Gerais, Brazil), Wagner Meira Jr. (Federal University of Minas Gerais, Brazil)
  3. Face-and-Clothing Based People Clustering in Video Content, Elie el Khoury (IRIT Laboratory, France), Christine Senac (IRIT Laboratory, France), Philippe Joly (IRIT Laboratory, France)
  4. Region-Based Automatic Web Image Selection, Keiji Yanai (Univ. of Electro-Communications, Japan), Kobus Barnard (University of Arizona)
  5. Stratification-based Keyframe Cliques for Removal of Near-Duplicates in Video Search Results, Xiangang Cheng (Nanyang Technological University, Singapore), Liang-Tien Chia (Nanyang Technological University, Singapore)
  6. Distances and Weighting Schemes for Bag of Visual Words Image Retrieval, Pierre Tirilly (IRISA / CNRS, France), Vincent Claveau (IRISA / CNRS, France), Patrick Gros (INRIA Rennes - Bretagne Atlantique, France)
  7. A Matrix Modular SVM Robust to Imbalanced Dataset for Efficient Visual Concept Detections, Herve Glotin (Univ. Sud Toulon-Var, France), Zhong-Qiu Zhao (Hefei University of Technology, China), Jun Gao (Hefei University of Technology, China), Xindong Wu (University of Vermont, USA)
  8. Beyond 2D-Grids: A Dependence Maximization View on Image Browsing, Novi Quadrianto (SML, NICTA and RSISE, ANU, Australia), Kristian Kersting (Fraunhofer IAIS, Germany), Tinne Tuytelaars (ESAT-PSI, KU Leuven, Belgium), Wray Buntine (SML, NICTA and RSISE, ANU, Australia)
  9. Wikipedia-assisted Concept Thesaurus for better Web Media Understanding, Huan Wang (Nanyang Technological University, Singapore), Liang-Tien Chia (Nanyang Technological University, Singapore)
  10. Combining Visual Features And Text Data For Medical Image Retrieval Using Latent Semantic Kernels, Juan C. Caicedo (National University of Colombia, Colombia), Jose G. Moreno (National University of Colombia, Colombia), Edwin A. Nino (National University of Colombia, Colombia), Fabio Gonzalez (National University of Colombia, Colombia)

B. Demos (Video Retrieval and 3D):

  1. NewsRoom: An Information-Seeking Support System for News Videos. Abdigani Diriye (University College London, UK), Srdan Zagorac (KMI, The Open University, UK), Suzanne Little (KMI, The Open University, UK), Stefan Rueger (KMI, The Open University, UK)
  2. SVE: an integrated system for Soccer Video Edition. Emna Fendri (Institut SupHrieur des Etudestechnologiques de Sfax, Tunisie), Siwar JALLOULI Fendri (Institut SupHrieur des Etudes technologiques de Sfax, Tunisie), Hanene BEN-ABDALLAH (FacultH des Sciences Economiqueset de Gestion de Sfax, Tunisie)
  3. The LIGVID System for Video Retrieval and Concept Annotation. Stephane Ayache (Laboratoire d'Informatique Fondamentale de Marseille, France), Georges Quinot (Laboratoire d'Informatique de Grenoble, France), Andy Tseng (Laboratoire d'Informatique de Grenoble, France)
  4. Sharing of Baseball Event through Social Media. Hogun Park (Korea Institute of Scienceand Technology, South Korea), Sun-Bum Youn (Korea Institute of Science and Technology, South Korea), Eugene Hong (Korea Institute of Science and Technology, South Korea), Changhyeon Lee (Korea Institute of Science and Technology, South Korea), Yong-moo Kwon (Korea Institute of Science and Technology, South Korea), Heedong Ko (Korea Institute of Science and Technology, South Korea), Myon-Woong Park (Intelligent Interaction Research Center Korea Institute of Science and Technology, South Korea), Young Tae Sohn (Intelligent Interaction Research Center Korea Institute of Science and Technology, South Korea), Jae Kwan Kim (Intelligent Interaction Research Center Korea Institute of Science and Technology, South Korea)
  5. Shape Rank: Efficient Web3D search technique using 3D features. Masahiro Ishikawa (Saitama university, Japan), Hiroshi Kawasaki (Saitama University, Japan), Ryo Furukawa (Hiroshima City University, Japan), Yukiko Kawai (Kyoto Sangyo University, Japan)

Close for the Day 5:00PM

Tuesday March 30, 2010

Registration: 8:00AM - 8:30AM

The registration desk will also be open throughout the event.

Industrial Leadership Invited Speakers Session: 8:30AM - 10:00AM
Chair: Nuria Oliver Ramirez (Telefonica R&D, Spain)

Coffee break 10:00AM - 10:20AM

Oral Session 2: 10:20AM - 12:00PM Multimedia Retrieval
Chair: Yixin Chen (University of Mississippi, USA)

  1. Multimodal Ranking for Image Search on Community Databases, Fabian Richter (University of Augsburg, Germany), Stefan Romberg (University of Augsburg, Germany), Eva Hörster (University of Augsburg, Germany), Rainer Lienhart (University of Augsburg, Germany)
  2. 3D Object Retrieval using Salient Views, Indriyati Atmosukarto (University of Washington, USA), Linda Shapiro (University of Washington, USA)
  3. Texture Image Retrieval Using Compact Texton Co-occurrence Matrix Descriptor, Qingyong Li (Beijing Jiaotong University, China), Zhiping Shi (Chinese Academy of Sciences, China)
  4. Incremental Indexing and Distributed Image Search using Shared Randomized Vocabularies, Raphael Maree (University of Liège, Belguim), Philippe Denis (University of Liège, Belguim), Louis Wehenkel (University of Liège, Belguim), Pierre Geurts (University of Liège, Belguim)
  5. Exploiting External Knowledge to Improve Video Retrieval, David Vallet (University of Glasgow, United Kingdom), Ivan Cantador (University of Glasgow, United Kingdom), Joemon M. Jose (University of Glasgow, United Kingdom)

Lunch break 12:00PM - 1:00PM

Mini Demo and Poster Introduction Session II: 1:00PM - 1:20PM (each talk is limited to one slide for about 1 minutes; 14 talks total)
Chair: Dhiraj Joshi (Eastman Kodak Research, USA)

Special Oral Session 2: 1:20PM - 3:00PM Statistical Modeling and Learning for Multimedia
Chair: C. Lee Giles (Penn State University, USA)
Organizers: Jia Li (Penn State University, USA), George Michailidis (University of Michigan, USA)

  1. Wavelet Coding Active Basis and Shape Script---A Tour in the Sparse Land, Zhangzhang Si (UCLA, USA), Ying Nian Wu (UCLA, USA)
  2. Understanding Word Association in News Media: A Sparse Classification Approach, Brian Gawalt (UC Berkeley, USA), Jinzhu Jia (UC Berkeley, USA), Luke Miratrix (UC Berkeley, USA), Laurent El Ghaoui (UC Berkeley, USA), Bin Yu (UC Berkeley, USA), Sophie Clavier (San Francisco State University, USA)
  3. Intensity Based Nonparametric Image Registration, Peihua Qiu (University of Minnesota, USA), Chen Xing (University of Minnesota, USA)
  4. Speculation on the Generality of the Backward Stepwise View of PCA, J. Steve Marron (University of North Carolina, USA), Sungkyu Jung (University of North Carolina, USA), Ian L. Dryden (University of South Carolina, USA)
  5. Quest for Relevant Tags Using Local Interaction Networks and Visual Content, Neela Sawant (Penn State University, USA), Ritendra Datta (Penn State University, USA, now with Google, USA), Jia Li (Penn State University, USA), James Z. Wang (Penn State University, USA)

Demo/Poster Session and Coffee Break (John C. Bogle Chairman's Room, 3:00PM - 4:00PM)
Chair: Dhiraj Joshi (Eastman Kodak Research, USA)
Note: The poster/demo room can only hold 75 people at a time.

A. Demos:

  1. Tag Dictionary and its Applications. Qingxiong Yang (University of Illinois at Urbana Champaign, USA), Bing Jian (Siemens Medical Solutions, USA), Xin Chen (NAVTEQ, USA)
  2. Analyzing Real Mobile Web Usage of a Multimedia Streaming Application through Log Files. Zahid Hussain (Technical University Graz, Austria)
  3. Controlling your TV with Gestures. Ming-yu Chen (Carnegie Mellon University, USA), Lily Mummert (Intel Labs Pittsburgh, USA), Padmanabhan Pillai(Intel Labs Pittsburgh, USA), Alex Hauptmann (Carnegie Mellon University, USA), Rahul Sukthankar (Intel Labs Pittsburgh, USA)
  4. Combinatorial ECG Analysis for Mobile Devices. Costas S. Iliopoulos (Kingms College London, UK), Spiros Michalakopoulos Iliopoulos (Kingms College London, UK)
  5. Eva - an evaluation tool for comparing descriptors in content-based image retrieval tasks. Ot7vio Penatti (University of Campinas, Brazil), Ricardo da S. Torres (University of Campinas, Brazil)
  6. QbS -- Searching for Known Images using User-Drawn Sketches. Michael Springmann (University of Basel, Switzerland), Dietmar Kopp (University of Basel, Switzerland), Heiko Schuldt (University of Basel, Switzerland)
  7. ACQUINE: Aesthetic Quality Inference Engine -- Real-time Automatic Rating of Photo Aesthetics. Ritendra Datta (The Pennsylvania State University, USA, now with Google, USA), James Z. Wang (The Pennsylvania State University, USA)
  8. Digimatge, a Rich Internet Application for Video Retrieval from a Multimedia Asset Management System. Xavier Giro-i-Nieto (Technical University of Catalonia, Spain), Ramon Salla (Catalan Broadcasting Corporation, Spain), Xavier Vives (Catalan Broadcasting Corporation, Spain)
  9. Meerkat: Using Tags to Control Internet Radio. Ashley M. Oudenne (Swarthmore College, USA), Youngmoo E. Kim (Drexel University, USA), Douglas S. Turnbull (Swarthmore College, USA)
  10. From microblogs to social images: Event analytics for situation assessment. Vivek K. Singh (University of California, Irvine, USA), Mingyan Gao (University of California, Irvine, USA), Ramesh Jain(University of California, Irvine, USA)
  11. Assessment of the Utility of Tag Clouds for Faster Image Retrieval. Johana Callegari (Kean University, USA), Patricia Morreale (Kean University, USA)
  12. Visualization for Increased Understanding and Learning Using Augmented Reality. Swetha Medicherla (Kean University, USA), George Chang (Kean University, USA), Patricia Morreale (Kean University, USA)
  13. Automatic Image Captioning From the Web For GPS Photographs. Xin Fan (University of Sheffield, UK), Ahmet Aker (University of Sheffield, UK), Martin Tomko (University of Zurich, Switzerland), Philip Smart (Cardiff University, UK), Mark Sanderson (University of Sheffield, UK), Robert Gaizauskas (University of Sheffield, UK)

B. Poster:

  1. SNDocRank: a Social Network-Based Video Search Ranking Framework, Liang Gou (Pennsylvania State University, USA), Hung-Hsuan Chen (Pennsylvania State University, USA), Jung-Hyun Kim (Pennsylvania State University, USA), Xiaolong (Luke) Zhang (Pennsylvania State University, USA), Lee Giles (Pennsylvania State University, USA)

Panel Session 4:00PM - 5:00PM: The Influence of Internet Hypes on Multimedia Information Retrieval Research
Chair: Alan Hanjalic (Delft University of Technology, The Netherlands)

Banquet 5:30PM - 9:00PM: at the National Constitution Center
Banquet Speech: Alberto Del Bimbo (University of Florence, Italy)

Wednesday March 31, 2010

Registration: 8:00AM - 8:30AM

The registration desk will also be open throughout the event.

Invited Talks: 8:30AM - 10:00AM
Chair: Nozha Boujemaa (INRIA, France)

Coffee break 10:00AM - 10:20AM

Oral Session 3: 10:20AM - 12:00PM Multimedia Copy Detection
Chair: Apostol Natsev (IBM Research, USA)

  1. AdaOUBoost: Adaptive Over-sampling and Under-sampling to Boost the Concept Learning in Large Scale Imbalanced Data sets, Yuxin Peng (Peking University, China), Jia Yao (Peking University, China)
  2. Effective and Scalable Video Copy Detection, Zhu Liu (AT&T, USA), Tao Liu (Polytechnic Institute of NYU, USA), David Gibbon (AT&T, USA), Behzad Shahraray (AT&T, USA)
  3. Robust Image Copy Detection Using Multi-resolution Histogram, Zhihua Xu (Huazhong University of Science and Technology, China), Hefei Ling (Huazhong University of Science and Technology, China), Fuhao Zou (Huazhong University of Science and Technology, China), Zhengding Lu (Huazhong University of Science and Technology, China), Ping Li (Huazhong University of Science and Technology, China)
  4. Sublinear Similarity Search of Realistic Timeseries and its Application to Human Motion, Omar U. Florez (Utah State University, USA), Alexander Ocsa (San Agustin University, Peru), Curtis Dyreson (Utah State University, USA)

Lunch break 12:00PM - 1:00PM

Mini Poster Introduction Session III: 1:00PM - 1:20PM (each talk is limited to one slide for about 1 minutes; 13 talks total)
Chair: Ritendra Datta (Google, USA)

Special Oral Session 3: 1:20PM - 3:20PM Multi-Modal Music Information Retrieval
Chair: Dan Ellis (Columbia University, USA), Youngmoo Kim (Drexel University, USA), Douglas Turnbull (Swarthmore College, USA)

  1. Multimodal Retrieval and Ranking: More than Waveforms, Malcolm Slaney (Yahoo! Research and Stanford CCRMA, USA)
  2. Integrating multi-modal data by metric learning, Brian McFee (UC San Diego, USA), Gert Lanckriet (UC San Diego, USA)
  3. Music Retrieval From Everything, Brian Whitman (The Echo Nest, USA), Tristan Jehan (The Echo Nest, USA), Paul Lamere (The Echo Nest, USA)
  4. Automated Analysis of Performance Variations in Folk Song Recordings, Meinard Muller (Utrecht University, The Netherlands), Peter Grosche (Utrecht University, The Netherlands), Frans Wiering (Utrecht University, The Netherlands)
  5. Improving Automatic Music Classification Performance by Extracting Features from Different Types of Data, Ichiro Fujinaga (McGill University, Canada), Cory McKay (McGill University, Canada)
  6. Feature Selection for Content-Based, Time-Varying Musical Emotion Regression, Erik Schmidt (Drexel University, USA), Douglas Turnbull (Drexel University, USA), Youngmoo Kim (Drexel University, USA)

Special Poster Session and Coffee Break (John C. Bogle Chairman's Room, 3:20PM - 4:40PM)
Chair: Ritendra Datta (Google, USA)

A. Processing Data Streams from Body Sensor Networks
Organizers: B. Prabhakaran (University of Texas at Dallas, USA), Deepak S. Turaga (IBM T. J. Watson Research Center, USA)

  1. Body Sensor Data Processing using Stream Computing, Alain Biem (IBM T. J. Watson Research Center, USA), Marion Blount (IBM T. J. Watson Research Center, USA), Maria Ebling (IBM T. J. Watson Research Center, USA), Daby Sow (IBM T. J. Watson Research Center, USA), Olivier Verscheure (IBM T. J. Watson Research Center, USA)
  2. Adaptive Sized Windows To Improve Real-Time Health Monitoring - A Case Study on Heart Attack Prediction, Morten Lindeberg (University of Oslo, Norway), Vera Goebel (University of Oslo, Norway), Thomas Plagemann (University of Oslo, Norway)
  3. Multimodal Analysis of Body Sensor Network Data Streams for Real-time Healthcare, Manoj K. Garg (University of Texas at Dallas, USA), Duk-Jin Kim (University of Texas at Dallas, USA), Deepak Turaga (IBM T. J. Watson Research Center, USA), Balakrishnan Prabhakaran (University of Texas at Dallas, USA)
  4. Processing Body Sensor Data Streams for Continuous Physiological Monitoring, Gaurav N. Pradhan (Arizona State University, USA), Rita Chattopadhyay (Arizona State University, USA), Sethuraman Panchanathan (Arizona State University, USA)

B. Multimedia Retrieval in Networked Communities
Organizers: Naeem Ramzan (Queen Mary University of London, UK), Martha Larson (Delft University of Technology, The Netherlands), Frédéric Dufaux (Ecole Polytechnique Fédérale de Lausanne, Switzerland), Kai Clüver (Technische Universität Berlin, Germany)

  1. The Participation Payoff: Challenges and Opportunities for Multimedia Access in Networked Communities, Naeem Ramzan (Queen Mary University of London, UK), Martha Larson (Delft University of Technology, The Netherlands), Frederic Dufaux (Ecole Polytechnique Federale de Lausanne, Switzerland), Kai Clüver (Technische Universität Berlin, Germany)
  2. Object-based Tag Propagation for Semi-Automatic Annotation of Images, Ivan Ivanov (Ecole Polytechnique Federale de Lausanne, Switzerland), Peter Vajda (Ecole Polytechnique Federale de Lausanne, Switzerland), Lutz Goldmann (Ecole Polytechnique Federale de Lausanne, Switzerland), Jong-Seok Lee (Ecole Polytechnique Federale de Lausanne, Switzerland), Touradj Ebrahimi (Ecole Polytechnique Federale de Lausanne, Switzerland)
  3. Semantic Structuring and Retrieval of Event Chapters in Social Photo Collections, Krishna Chandramouli (Queen Mary University of London, UK), Ebroul Izquierdo (Queen Mary University of London, UK)
  4. An Interactive Framework for Image Annotation through Gaming, Lasantha Seneviratne (Queen Mary University of London, UK), Ebroul Izquierdo (Queen Mary University of London, UK)

C. MIRFLICKR Evaluation: The Challenge of Visual Concept Detection
Organizers: Mark Huiskes (Leiden University, The Netherlands), M. S. Lew (Leiden University, The Netherlands)

  1. New Trends and Ideas in Visual Concept Detection, Mark J. Huiskes (Leiden University, The Netherlands), Bart Thomee (Leiden University, The Netherlands), Michael S. Lew (Leiden University, The Netherlands)
  2. Image Annotation with TagProp on the MIRFLICKR set, Jakob Verbeek (INRIA Rhone-Alpes, France), Matthieu Guillaumin (INRIA Rhone-Alpes, France), Thomas Mensink (Xerox Research Centre Europe, France), Cordelia Schmid (INRIA Rhone-Alpes, France)
  3. Automatically Annotating the MIR Flickr Dataset, Jonathan S. Hare (University of Southampton, UK), Paul H. Lewis (University of Southampton, UK)
  4. How reliable are Annotations via Crowdsourcing?, Stefanie Nowak (Fraunhofer IDMT, Germany)
  5. Minimum Explanation Complexity for MOD based Visual Concept Detection, Ard Oerlemans (VDG Security, USA), Michael S. Lew (Leiden University, The Netherlands)

Closing Remark and Introduction of ACM ICMR2011 (new name for MIR) 4:40PM - 5:00PM
Nozha Boujemaa (INRIA, France) and Alberto Del Bimbo (University of Florence, Italy)

Conference Adjourn 5:00PM


Last updated: March 25, 2010.