Event Reports

Reports from SIGMM Sponsored and Co-sponsored Events

ACM Multimedia Information Retrieval 2010

The 2010 ACM SIG Multimedia International Conference on Multimedia Information Retrieval (MIR) was held at the National Constitution Center, Philadelphia, Pennsylvania, in late March. The search for digital information is one of the major challenges of our time. Digital libraries, biomedical sciences, the Internet and social networking sites, streaming video, multimedia databases, cultural heritage collections and peer-to-peer networks have created a worldwide need for new paradigms and techniques on how to browse, search and summarize multimedia collections and more generally how to afford efficient multimedia content consumption. The main aim of this conference was to present innovative solutions to tackle this global challenge.

After a rigorous peer-review process, the MIR Program Committee selected 14 contributions to include in the program as regular papers and an additional 11 as poster papers. There were also oral and poster special sessions on emerging frontier theories and applications. Their session proposals were peer-reviewed. The session organizers selected the papers. The themes of these sessions were (1) medical retrieval, (2) statistical modeling and learning, (3) multi-modal music retrieval, (4) body sensor networks, (5) networked communities, and (6) evaluation for visual concept detection. A demo session showcased some of the latest technologies and prototype systems.

The conference featured outstanding keynote and invited speakers. They were B.S. Manjunath, Professor of the University of California at Santa Barbara, Alberto Del Bimbo, Professor of the University of Florence, and Gregory Grefenstette, Chief Science Officer of Exalead. Additionally, an Industrial Leadership Invited Speaker Session featured a few of the latest R&D efforts in the industry. Speakers of the session were (1) Behzad Shahraray, Executive Director, Video and Multimedia Technologies Research, AT&T Labs, (2) Dhiraj Joshi, Research Scientist, Intelligent Systems Group, Eastman Kodak Research Labs, (3) Alwar Narayanan, Director of Research and Emerging Technologies, NAVTEQ Corporation, and (4) Apostol (Paul) Natsev, Research Staff Member and Manager, IBM T.J. Watson Research Center.

The panel this year, moderated by Alan Hanjalic, concentrated on the influence of Internet hypes on research in our field. The panelists included Nuria Oliver Ramirez, Apostol Natsev, Alberto Del Bimbo, and Michael Lew.

Starting in 2011, the Multimedia Information Retrieval (MIR) and the Image and Video Retrieval (CIVR) conference series will merge to create the ACM International Conference on Multimedia Retrieval (ICMR) series. The ICMR conference series will continue to illuminate the state of the art in our field by bringing together active researchers and practitioners. We hope that researchers will contribute by sharing their finest research findings at ICMR. The forthcoming ICMR will be located in Trento, Italy, in April 2011.

Papers

Academic keynote address

• B. S. Manjunath
  Bioimage informatics: recent advances and challenges

Industrial leadership invited speakers session

• Behzad Shahraray
  Multimedia processing for advanced content services
• Dhiraj Joshi
  Semantic understanding of geotagged pictures
• Alwar Narayanan
  Next generation map making: automation from mobile data collection
• Apostol (Paul) Natsev
  Multimedia semantics: opportunities and challenges

Invited talks

• Gregory Grefenstette
  Implementing a content-based public-oriented audio and video news retrieval system
• Stephen M. Griffin
  Recovering the past through computation: new techniques for cultural heritage

Oral session 1: multimedia analysis

• Tanveer Fathima Syeda-Mahmood, Fei Wang, David Beymer
  Recognition of object categories using affine kernels
• Damian Borth, Adrian Ulges, Thomas M. Breuel
  Relevance filtering meets active learning: improving web-based concept detectors
• Stefanie Nowak, Hanna Lukashevich, Peter Dunker, Stefan Rüger
  Performance measures for multilabel evaluation: a case study in the area of image classification
• Yuanning Li, Yonghong Tian, Jingjing Yang, Ling-Yu Duan, Wen Gao
  Video retargeting with multi-scale trajectory optimization
• Derek Tingle, Youngmoo E. Kim, Douglas Turnbull
  Exploring automatic music annotation with "acoustically-objective" tags

Oral session 2: multimedia retrieval

• Fabian Richter, Stefan Romberg, Eva Hörster, Rainer Lienhart
  Multimodal ranking for image search on community databases
• Indriyati Atmosukarto, Linda G. Shapiro
  3d object retrieval using salient views
• Qingyong Li, Zhiping Shi
  Texture image retrieval using compact texton co-occurrence matrix descriptor
• Raphaël Marée, Philippe Denis, Louis Wehenkel, Pierre Geurts
  Incremental indexing and distributed image search using shared randomized vocabularies
• David Vallet, Iván Cantador, Joemon M. Jose
  Exploiting external knowledge to improve video retrieval

Oral session 3: multimedia copy detection

• Yuxin Peng, Jia Yao
  AdaOUBoost: adaptive over-sampling and under-sampling to boost the concept learning in large scale imbalanced data sets
• Zhu Liu, Tao Liu, David C. Gibbon, Behzad Shahraray
  Effective and scalable video copy detection
• Zhihua Xu, Hefei Ling, Fuhan Zou, Zhengding Lu, Ping Li
  Robust image copy detection using multi-resolution histogram
• Omar U. Florez, Alexander Ocsa, Curtis Dyreson
  Sublinear querying of realistic timeseries and its application to human motion

Special oral session 1: medical multimedia retrieval

• Md Mahmudur Rahman, Sameer K. Antani, George R. Thoma
  A classification-driven similarity matching framework for retrieval of biomedical images
• Uri Avni, Jacob Goldberger, Michal Sharon, Eli Konen, Hayit Greenspan
  Chest x-ray characterization: from organ identification to pathology categorization
• Jayashree Kalpathy-Cramer, William Hersh
  Multimodal medical image retrieval: image categorization to improve search precision
• Xiang Sean Zhou, Zhigang Peng, Yiqiang Zhan, Maneesh Dewan, Bing Jian, Arun Krishnan, Yimo Tao, Martin Harder, Stefan Grosskopf, Ute Feuerlein
  Redundancy, redundancy, redundancy: the three keys to highly robust anatomical parsing in medical images
• Robert Kim, Grace Dasovich, Runa Bhaumik, Richard Brock, Jacob D. Furst, Daniela S. Raicu
  An investigation into the relationship between semantic and content based similarity using LIDC
• Devrim Unay
  Augmenting clinical observations with visual features from longitudinal MRI data for improved dementia diagnosis

Special oral session 2: statistical modeling and learning for multimedia

• Zhangzhang Si, Ying Nian Wu
  Wavelet, active basis, and shape script: a tour in the sparse land
• Brian Gawalt, Jinzhu Jia, Luke Miratrix, Laurent El Ghaoui, Bin Yu, Sophie Clavier
  Discovering word associations in news media via feature selection and sparse classification
• Peihua Qiu, Chen Xing
  Intensity based nonparametric image registration
• J S. Marron, Sungkyu Jung, Ian L. Dryden
  Speculation on the generality of the backward stepwise view of PCA
• Neela Sawant, Ritendra Datta, Jia Li, James Z. Wang
  Quest for relevant tags using local interaction networks and visual content

Special oral session 3: multi-modal music information retrieval

• Malcolm Slaney
  Multimodal retrieval and ranking: more than waveforms
• Brian McFee, Gert Lanckriet
  Learning similarity in heterogeneous data
• Tristan Jehan, Paul Lamere, Brian Whitman
  Music retrieval from everything
• Meinard Müller, Peter Grosche, Frans Wiering
  Automated analysis of performance variations in folk song recordings
• Cory McKay, Ichiro Fujinaga
  Improving automatic music classification performance by extracting features from different types of data
• Erik M. Schmidt, Douglas Turnbull, Youngmoo E. Kim
  Feature selection for content-based, time-varying musical emotion regression

Poster session: Multimedia information retrieval

• Jörn Wanke, Adrian Ulges, Christoph H. Lampert, Thomas M. Breuel
  Topic models for semantics-preserving video compression
• Fabio F. Faria, Adriano Veloso, Humberto M. Almeida, Eduardo Valle, Ricardo da S. Torres, Marcos A. Gonçalves, Wagner Meira, Jr.
  Learning to rank for content-based image retrieval
• Elie El Khoury, Christine Senac, Philippe Joly
  Face-and-clothing based people clustering in video content
• Keiji Yanai, Kobus Barnard
  Region-based automatic web image selection
• Xiangang Cheng, Liang-Tien Chia
  Stratification-based keyframe cliques for removal of near-duplicates in video search results
• Pierre Tirilly, Vincent Claveau, Patrick Gros
  Distances and weighting schemes for bag of visual words image retrieval
• Herve Glotin, Zhong-Qiu Zhao, Jun Gao, Xindong Wu
  A matrix modular SVM robust to imbalanced data for efficient visual concept detection
• Novi Quadrianto, Kristian Kersting, Tinne Tuytelaars, Wray L. Buntine
  Beyond 2D-grids: a dependence maximization view on image browsing
• Huan Wang, Liang-Tien Chia, Shenghua Gao
  Wikipedia-assisted concept thesaurus for better web media understanding
• Juan C. Caicedo, Jose G. Moreno, Edwin A. Niño, Fabio A. González
  Combining visual features and text data for medical image retrieval using latent semantic kernels
• Liang Gou, Hung-Hsuan Chen, Jung-Hyun Kim, Xiaolong (Luke) Zhang, C. Lee Giles
  SNDocRank: a social network-based video search ranking framework

Demo session 1: demos on video retrieval and 3D

• Abdigani Diriye, Srdan Zagorac, Suzanne Little, Stefan Rüger
  NewsRoom: an information-seeking support system for news videos
• Emna Fendri, Siwar Jallouli, Hanene Ben-Abdallah
  SVE: an integrated system for soccer video edition
• Stéphane Ayache, Georges Quénot, Andy Tseng
  The lIGVID system for video retrieval and concept annotation
• Hogun Park, Sun-Bum Youn, Eugene Hong, Changhyeon Lee, Yong-moo Kwon, Heedong Ko, Myon-Woong Park, Young Tae Sohn, Jae Kwan Kim
  Sharing of baseball event through social media
• Masahiro Ishikawa, Hiroshi Kawasaki, Ryo Furukawa, Yukiko Kawai
  Shape rank: efficient web3D search technique using 3D features

Demo session 2: demos on multimedia information retrieval

• Qingxiong Yang, Bing Jian, Xin Chen
  Tag dictionary and its applications
• Zahid Hussain, Wolfgang Slany
  Analyzing real mobile web usage of a multimedia streaming application through log files
• Ming-yu Chen, Lily Mummert, Padmanabhan Pillai, Alexander Hauptmann, Rahul Sukthankar
  Controlling your TV with gestures
• Costas S. Iliopoulos, Spiros Michalakopoulos
  Combinatorial ECG analysis for mobile devices
• Otávio A.B. Penatti, Ricardo da S. Torres
  Eva: an evaluation tool for comparing descriptors in content-based image retrieval tasks
• Michael Springmann, Dietmar Kopp, Heiko Schuldt
  QbS: searching for known images using user-drawn sketches
• Ritendra Datta, James Z. Wang
  ACQUINE: aesthetic quality inference engine - real-time automatic rating of photo aesthetics
• Xavier Giro-i-Nieto, Ramon Salla, Xavier Vives
  Digimatge, a rich internet application for video retrieval from a multimedia asset management system
• Ashley M. Oudenne, Youngmoo E. Kim, Douglas S. Turnbull
  Meerkat: exploring semantic music discovery using personalized radio
• Vivek K. Singh, Mingyan Gao, Ramesh Jain
  From microblogs to social images: event analytics for situation assessment
• Johana Callegari, Patricia Morreale
  Assessment of the utility of tag clouds for faster image retrieval
• Padmavathi S. Medicherla, George Chang, Patricia Morreale
  Visualization for increased understanding and learning using augmented reality
• Xin Fan, Ahmet Aker, Martin Tomko, Philip Smart, Mark Sanderson, Robert Gaizauskas
  Automatic image captioning from the web for GPS photographs

Special poster session 1: processing data streams from body sensor networks

• Daby Sow, Alain Biem, Marion Blount, Maria Ebling, Olivier Verscheure
  Body sensor data processing using stream computing
• Morten Lindeberg, Vera Goebel, Thomas Plagemann
  Adaptive sized windows to improve real-time health monitoring: a case study on heart attack prediction
• Manoj K. Garg, Duk-Jin Kim, Deepak S. Turaga, Balakrishnan Prabhakaran
  Multimodal analysis of body sensor network data streams for real-time healthcare
• Gaurav N. Pradhan, Rita Chattopadhyay, S. Panchanathan
  Processing body sensor data streams for continuous physiological monitoring

Special poster session 2: multimedia retrieval in networked communities

• Naeem Ramzan, Martha Larson, Frédéric Dufaux, Kai Clüver
  The participation payoff: challenges and opportunities for multimedia access in networked communities
• Ivan Ivanov, Peter Vajda, Lutz Goldmann, Jong-Seok Lee, Touradj Ebrahimi
  Object-based tag propagation for semi-automatic annotation of images
• Krishna Chandramouli, Ebroul Izquierdo
  Semantic structuring and retrieval of event chapters in social photo collections
• Lasantha Seneviratne, Ebroul Izquierdo
  An interactive framework for image annotation through gaming

Special poster session 3: MIRFLICKR evaluation: the challenge of visual concept detection

• Mark J. Huiskes, Bart Thomee, Michael S. Lew
  New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative
• Jakob Verbeek, Matthieu Guillaumin, Thomas Mensink, Cordelia Schmid
  Image annotation with tagprop on the MIRFLICKR set
• Jonathon S. Hare, Paul H. Lewis
  Automatically annotating the MIR Flickr dataset: experimental protocols, openly available data and semantic spaces
• Stefanie Nowak, Stefan Rüger
  How reliable are annotations via crowdsourcing: a study about inter-annotator agreement for multi-label image annotation
• Ard Oerlemans, Michael S. Lew
  Minimum explanation complexity for MOD based visual concept detection

Panel Session: The influence of internet hypes on multimedia information retrieval research

• Alan Hanjalic
  The influence of internet hypes on multimedia information retrieval research

TOMCCAP, Volume 6, Issue 3, August 2010

Papers

• Changsheng Xu, Eckehard Steinbach, Abdulmotaleb El Saddik, Michelle Zhou:
  Introduction to the best papers of ACM multimedia 2009
• Zheng-Jun Zha, Linjun Yang, Tao Mei , Meng Wang, Zengfu Wang, Tat-Seng Chua, Xian-Sheng Hua:
  Visual query suggestion: Towards capturing user intent in internet image search
• Wei Jiang, Courtenay Cotton, Shih-Fu Chang, Dan Ellis, Alexander C. Loui:
  Audio-visual atoms for generic video concept classification
• Rodrigo De Oliveira, Mauro Cherubini, Nuria Oliver:
  Looking at near-duplicate videos from a human-centric perspective
• Hao Yin, Xuening Liu, Tongyu Zhan, Vyas Sekar, Feng Qiu, Chuang Lin, Hui Zhang, Bo Li:
  LiveSky: Enhancing CDN with P2P
• Arthur G. Money, Harry Agius:
  ELVIS: Entertainment-led video summaries
• Steven C.h. Hoi, Wei Liu, Shih-Fu Chang:
  Semi-supervised distance metric learning for collaborative image retrieval and clustering
• Namunu C. Maddage, Khe Chai Sim, Haizhou Li:
  Word level automatic alignment of music and lyrics using vocal synthesis
• Bashar Qudah, Nabil J. Sarhan:
  Efficient delivery of on-demand video streams to heterogeneous receivers
• João P. Gomes, Pedro R. M. Inácio, Branka Lakic, Mário M. Freire, Henrique J. A. Da Silva, Paulo P. Monteiro:
  Source traffic analysis

Reports from other ACM Events

MMSJ, Volume 16, Issue 4-5, August 2010

Papers

• Zhiwen Yu, Artur Lugmayr, Konstantinos Chorianopoulos and Tao Mei:
  Introduction to the special issue on multimedia intelligent services and technologies
• Theodora Nanou, George Lekakos and Konstantinos Fouskas:
  The effects of recommendations' presentation on persuasion and satisfaction in a movie recommender system
• Zhiwen Yu, Xingshe Zhou, Liang Zhou and Kejun Du:
  A hybrid similarity measure of contents for TV personalization
• Peizhao Hu, Wee Lum Tan, Ryan Wishart, Marius Portmann and Jadwiga Indulska:
  MeshVision: an adaptive wireless mesh network video surveillance system
• Frank Hopfgartner and Joemon M. Jose:
  Semantic user profiling techniques for personalised multimedia recommendation
• Jung-Hyun Kim, Hyeong-Joon Kwon and Kwang-Seok Hong:
  Location awareness-based intelligent multi-agent technology
• Wei Zhang, Bo Begole and Maurice Chu:
  Asynchronous reflections: theory and practice in the design of multimedia mirror systems
• Frode Eika Sandnes:
  Where was that photo taken? Deriving geographical information from image collections based on temporal exposure attributes
• Zhenbao Liu, Zhongsheng Wang, Cunbao Ma, Chao Zhang, Jun Mitani and Yukio Fukui:
  Shape alignment and shape orientation analysis-based 3D shape retrieval system
• Tao Mei, Jinlian Guo, Xian-Sheng Hua and Falin Liu:
  AdOn: toward contextual overlay in-video advertising