SIGMM Records Event Reports

Reports from SIGMM Sponsored and Co-sponsored Events

International Conference on Content-based Image and Video Retrieval

The International Conference on Content-based Image and Video Retrieval (CIVR) is a prominent technical conference in this field. Since 2007, CIVR has now become an official ACM Conference and an IAPR co-sponsored event (thanks to the initiatives by 2007 co-chairs Marcel Worring and Nicu Sebe).

The 2008 edition was held in Sheraton Fallsview in Niagara Falls, Ontario, on July 7-9, with Jiebo luo as the general chair and Ling Guan as the general co-chair. CIVR is the dedicated annual professional meeting for communicating the state-of-the-art research and technology in image and video retrieval. As in previous years, starting with the first CIVR conference in 2002 and continuing to the first ACM-branded CIVR in 2007, the conference seeks to illuminate the state of the art in image and video retrieval between researchers and practitioners throughout the world and provide an international forum for the discussion of challenges in the fields of image and video retrieval. In a nutshell, CIVR covers all aspects of image and video retrieval, from underlying technologies and theories to applications and practice. The three-day conference consisted of three major parts: the regular and special sessions tracks on Monday and Tuesday, a full Practitioner's Day on Wednesday, and the VideoOlympics exhibition showcasing live-action video search and retrieval. We were excited to host two research keynote presentations by Prof. Jiawei Han of the University of Illinois at Urbana-Champaign and Prof. Alberto Del Bimbo of University of Florence, as well as one application keynote by Dr. Edward Chang of Google Research China.

The program co-chairs, Alan Hanjalic, Mohan Kankanhalli, and Ivan Lee, were responsible, along with a program committee of 70 members, for selecting the full paper program for the regular paper track. The regular paper track received 123 paper submissions. The rigorous review process resulted in the acceptance of 15 oral presentations and 42 poster presentations. This represents an acceptance rate of 12% for oral and 34% overall.

To highlight important and emerging topics, the number of special sessions increased from one in 2007 to three in the research track and one in the practitioner track in 2008. The special sessions co-chairs Lexing Xie and Qi Tian did an excellent job identifying and coordinating the various special topics. The co-chairs of the Practitioners' Day program, James Wang and Nozha Boujemaa, put together an impressive line-up of talks for the application side of CIVR. The co-chairs of the VideoOlympics, Marcel Worring, Cees Snoek, Rong Yan, and Alex Hauptmann, made the much anticipated event another great success with more participating teams and highly involved audience. All the organizers put in an enormous amount of work to bring an exciting and high quality conference, and their contributions are much appreciated by us and the entire CIVR community. In particular, Ivan Lee received a special recognition for doing double and triple duties for the conference since its genesis (and well after the conference concluded).

With the strong technical program and social program, the second highest participation in its history, and healthy finance, the CVIR 2008 conference was a great success.

The next CIVR will be held in July 8-10, 2009 in the Island of Santorini, Greece. Please visit http://www.civr2009.org

Papers

Introduction

• Jiawei Han:
  Data mining for image/video processing: a promising research frontier.

Tagging, training and classification

• Simon J. Laing:
  Applying graphic design terms to image tagging.
• Adrian Ulges, Christian Schulze, Daniel Keysers, Thomas M. Breuel:
  Identifying relevant frames in weakly labeled videos for training concept detectors.
• Mei Wang, Xiangdong Zhou, Tat-Seng Chua:
  Automatic image annotation via local multi-label classification.
• Hao Cheng, Kien A. Hua, Khanh Vu:
  Leveraging user query log: toward improving image data clustering.
• Dhiraj Joshi, Jiebo Luo:
  Inferring generic activities and events from image content and bags of geo-tags.

Objects, events and concepts

• Till Quack, Bastian Leibe, Luc J. Van Gool:
  World-scale mining of objects and events from community photo collections.
• Zhikun Wang, Dong Wang, Jianmin Li, Bo Zhang:
  Learning structured concept-segments for interactive video retrieval.
• Weijun Wang, Yupin Luo, Guangrong Tang:
  Object retrieval using configurations of salient regions.
• Brendan Elliott, Z. Meral Özsoyoglu:
  Annotation suggestion and search for personal multimedia objects on the web.
• Jun Yang, Alexander G. Hauptmann:
  (Un)Reliability of video concept detection.

Subspace learning in content-based image retrieval

• Hongli Xu, Dantong Yu, De Xu, Aidong Zhang:
  SS-ClusterTree: a subspace clustering based indexing algorithm over high-dimensional image features.
• Jiayu Tang, Paul H. Lewis:
  Non-negative matrix factorisation for object class discovery and image auto-annotation.
• Changhu Wang, Lei Zhang, Hong-Jiang Zhang:
  Scalable Markov model-based image annotation.
• Wei Liu, Wei Jiang, Shih-Fu Chang:
  Relevance aggregation projections for image retrieval.
• Yun Fu, Liangliang Cao, Guodong Guo, Thomas S. Huang:
  Multiple feature fusion by subspace learning.

Poster/reception

• Yue Gao, Qiong-Hai Dai:
  Clip based video summarization and ranking.
• Koen E. A. van de Sande, Theo Gevers, Cees G. M. Snoek:
  A comparison of color features for visual concept classification.
• Alexandros Ntousias, Nektarios Gioldasis, Chrisa Tsinaraki, Stavros Christodoulakis:
  Rich metadata and context capturing through CIDOC/CRM and MPEG-7 interoperability.
• Yantao Zheng, Shi-Yong Neo, Tat-Seng Chua, Qi Tian:
  Probabilistic optimized ranking for multimedia semantic concept detection via RVM.
• Jie Yu, Jiebo Luo:
  Leveraging probabilistic season and location context models for scene understanding.
• Aiwen Jiang, Chunheng Wang, Baihua Xiao:
  Scene modeling in global-local view for scene classification.
• Kiyoko Iwasaki, Masayuki Kanbara, Kazumasa Yamazawa, Naokazu Yokoya:
  Construction of extended geographical database based on photo shooting history.
• Michael Blighe, Noel E. O'Connor:
  MyPlaces: detecting important settings in a visual diary.
• Hamed Shahbazi, Mohsen Soryani, Peyman Kabiri:
  Content based multispectral image retrieval using principal component analysis.
• Nicolas Gengembre, Sid-Ahmed Berrani:
  A probabilistic framework for fusing frame-based searches within a video copy detection system.
• Georgios Th. Papadopoulos, Vasileios Mezaris, Ioannis Kompatsiaris, Michael G. Strintzis:
  Accumulated motion energy fields estimation and representation for semantic event detection.
• Wen Wu, Jie Yang:
  Semi-supervised learning of object categories from paired local features.
• Mark J. Huiskes, Michael S. Lew:
  Performance evaluation of relevance feedback methods.
• Pierre Tirilly, Vincent Claveau, Patrick Gros:
  Language modeling for bag-of-visual words image categorization.
• Aiden R. Doherty, Daragh Byrne, Alan F. Smeaton, Gareth J. F. Jones, Mark Hughes:
  Investigating keyframe selection methods in the novel domain of passively captured visual lifelogs.
• Pierre-Alain Moëllic, Jean-Emmanuel Haugeard, Guillaume Pitel:
  Image clustering based on a shared nearest neighbors approach for tagged collections.
• Felix Lee, Werner Bailer:
  Organizing rushes video by visually similar setting.
• Roberto Vezzani, Simone Calderara, Paolo Piccinini, Rita Cucchiara:
  Smoke detection in video surveillance: the use of ViSOR (video surveillance on-line repository).
• Daragh Byrne, Peter Wilkins, Gareth J. F. Jones, Alan F. Smeaton, Noel E. O'Connor:
  Measuring the impact of temporal context on video retrieval.
• Pinaki Sinha, Ramesh Jain:
  Classification and annotation of digital photos using optical context data.
• Eva Hörster, Rainer Lienhart, Malcolm Slaney:
  Continuous visual vocabulary modelsfor pLSA-based scene recognition.
• Stavros Petridis, Maja Pantic:
  Fusion of audio and visual cues for laughter detection.
• Madirakshi Das, Jens Farmer, Andrew C. Gallagher, Alexander C. Loui:
  Event-based location matching for consumer image collections.
• Robin Aly, Djoerd Hiemstra, Arjen P. de Vries, Franciska de Jong:
  A probabilistic ranking framework using unobservable binary events for video search.
• Jonathon S. Hare, Sina Samangooei, Paul H. Lewis, Mark S. Nixon:
  Semantic spaces revisited: investigating the performance of auto-annotation and semantic retrieval using semantic spaces.
• Pradhee Tandon, Piyush Nigam, Vikram Pudi, C. V. Jawahar:
  FISH: a practical system for fast interactive image search in huge databases.
• Bart Kroon, Alan Hanjalic, Sander M. P. Maas:
  Eye localization for face matching: is it always useful and under what conditions?
• Kambiz Jarrah, Ling Guan:
  Content-based image retrieval via distributed databases.
• Stefano Berretti, Alberto Del Bimbo, Pietro Pala:
  3D face retrieval using integral geometric shape information.

Improving the quality of retrieval

• Hung-sik Kim, Jeongkyu Lee, Haibin Liu, Dongwon Lee:
  Video linkage: group based copied video detection.
• Michael G. Christel, Wei-Hao Lin, Bryan Maher:
  Evaluating audio skimming and frame rate acceleration for summarizing BBC rushes.
• Radu Andrei Negoescu, Daniel Gatica-Perez:
  Analyzing Flickr groups.
• Shaolei Feng, Raghavan Manmatha:
  A discrete direct retrieval model for image and video retrieval.
• Alexander Haubold, Apostol Natsev:
  Web-based information content and its application to concept-based video retrieval.

Challenges in interactive video retrieval

• Michael G. Christel:
  Supporting video library exploratory search: when storyboards are not enough.
• Huan-Bo Luan, Yantao Zheng, Shi-Yong Neo, Yongdong Zhang, Shouxun Lin, Tat-Seng Chua:
  Adaptive multiple feedback strategies for interactive video search.
• John Adcock, Matthew Cooper, Jeremy Pickens:
  Experiments in interactive video search by addition and subtraction.
• Rong Yan, Apostol Natsev, Murray Campbell:
  Multi-query interactive image and video retrieval -: theory and practice.
• Ork de Rooij, Cees G. M. Snoek, Marcel Worring:
  Balancing thread based navigation for targeted video search.

Visual systems for event analysis in sports

• Xinguo Yu, Xin Yan, Liyuan Li, Hon Wai Leong:
  An instant semantics acquisition system of live soccer video with application to live event alert and on-the-fly language selection.
• Jun Miura, Hiroyuki Kubo:
  Tracking players in highly complex scenes in broadcast soccer video using a constraint satisfaction approach.
• Guangyu Zhu, Changsheng Xu, Yi Zhang, Qingming Huang, Hanqing Lu:
  Event tactic analysis based on player and ball trajectory in broadcast video.
• Marco Leo, Nicola Mosca, Paolo Spagnolo, Pier Luigi Mazzeo, Tiziana D'Orazio, Arcangelo Distante:
  Real-time multiview analysis of soccer matches for understanding interactions between ball and players.
• Gabin Kayumbi, Pier Luigi Mazzeo, Paolo Spagnolo, Murtaza Taj, Andrea Cavallaro:
  Distributed visual sensing for virtual top-view trajectory generation in football videos.

Video retrieval showcase

• Alexander G. Hauptmann, Jonathan J. Wang, Wei-Hao Lin, Jun Yang, Michael G. Christel:
  Efficient search: the informedia video retrieval system.
• Eric Zavesky, Shih-Fu Chang:
  Columbia University's semantic video search engine 2008.
• Alan F. Smeaton, Colum Foley, Daragh Byrne, Gareth J. F. Jones:
  iBingo mobile collaborative search.
• Zichen Sun, Yuanzheng Song, Yingbin Zheng, Hui Yu, Cheng Jin, Hong Lu, Xiangyang Xue:
  Fudan University: hierarchical video retrieval with adaptive multi-modal fusion.
• John Adcock, Jeremy Pickens:
  FXPAL collaborative exploratory video search system.
• Apostol Natsev, John R. Smith, Jelena Tesic, Lexing Xie, Rong Yan:
  IBM multimedia analysis and retrieval system.
• Peter Wilkins, Alan F. Smeaton, Noel E. O'Connor, Daragh Byrne:
  K-Space Interactive Search.
• Stéphane Ayache, Georges Quénot:
  The LIG multi-criteria system for video retrieval.
• Shi-Yong Neo, Huan-Bo Luan, Yantao Zheng, Hai-Kiat Goh, Tat-Seng Chua:
  VisionGo: bridging users and multimedia video retrieval.
• Ork de Rooij, Cees G. M. Snoek, Marcel Worring:
  MediaMill: fast and effective video search using the forkbrowser.
• Stefanos Vrochidis, Paul King, Lambros Makris, Anastasia Moumtzidou, Vasileios Mezaris, Ioannis Kompatsiaris:
  MKLab interactive video retrieval system.
• James Philbin, Andrew Zisserman:
  University of Oxford video retrieval system.
• Jianmin Li, Zhikun Wang, Dong Wang, Bo Zhang:
  Interactive video retrieval with rich features and friendly interface.
• Edward Y. Chang:
  Organizing multimedia data socially.

Real-world challenges

• Xiang Sean Zhou, Sonja Zillner, Manuel Möller, Michael Sintek, Yiqiang Zhan, Arun Krishnan, Alok Gupta:
  Semantics and CBIR: a medical imaging perspective.
• Brian A. Canada, Georgia K. Thomas, Keith C. Cheng, James Ze Wang, Yanxi Liu:
  Towards efficient automated characterization of irregular histology images via transformation to frieze-like patterns.
• Qingxiong Yang, Xin Chen, Gang Wang:
  Web 2.0 dictionary.
• Mauro Barbieri, Pedro Fonseca, Marc A. Peters, Lu Wang:
  Multimedia content analysis for consumer electronics.
• Marie-Luce Viaud, Jérôme Thièvre, Hervé Goeau, Agnès Saulnier, Olivier Buisson:
  Interactive components for visual exploration of multimedia archives.

Three screen services and technologies

• Eric Zavesky, Shih-Fu Chang, Cheng-Chih Yang:
  Visual islands: intuitive browsing of visual search results.
• Xiaofeng Wang, Xiao-Ping Zhang, Ian Clarke, Yury Yakubovich:
  A new room decoration assistance system based on 3D reconstruction and integrated service.
• Zhu Liu, David C. Gibbon, Harris Drucker, Andrea Basso:
  Content personalization and adaptation for three-screen services.
• Zhen Xiao, Fan Ye:
  New insights on internet streaming and IPTV.
• Yang Guo, Chao Liang, Yong Liu:
  dHCPS: decentralized hierarchically clustered p2p video streaming.

Panel

• Aidong Zhang, Shih-Fu Chang, Arif Ghafoor, Thomas S. Huang, Ramesh Jain, Rainer Lienhart:
  Future directions in multimedia retrieval: impact of new technology.

TOMCCAP Volume 5 Issue 2

Volume 5, Number 2, May 2009

The Transactions on Multimedia Computing, Communication and Applications are the SIGMM's own Transactions. As a service to Records readers, we provide direct links to ACM Digital Library for the papers of the latest TOMCCAP issue. This issue is Volume, Number 2 and has come into print in May 2009. It is a regular issue, containing papers that have been submitted freely and peer-reviewed by three reviewers according to standard procedure. The topics span the entire range of multimedia topics, from improvements in wireless access control to the use of social contexts. We hope that you enjoy the issue.

Looking at the digital library, you may be confused that its publication date is given as December 2008. The maintainers for the digital library explain that the reason for this is that ACM has decided to list the date of publication in the digital library as the publication date, rather than the printing date of the paper issue. This means that you will see this in all future editions as well.

Papers

• Simon Moncrieff, Svetha Venkatesh, Geoff A. W. West:
  Dynamic privacy assessment in a smart house environment using multimodal sensing.

• Brett Adams, Dinh Q. Phung, Svetha Venkatesh:
  Sensing and using social context.

• Saraju P. Mohanty, Bharat K. Bhargava:
  Invisible watermarking based on creation and robust insertion-extraction of image adaptive watermarks.

• Wai-Pun Ken Yiu, Shueng-Han Gary Chan:
  Offering data confidentiality for multimedia overlay multicast: Design and analysis.

• Minoru Nakayama, Yosiyuki Takahasi:
  Estimation of certainty for responses to multiple-choice questionnaires using eye movements.

• Frank Shipman, Andreas Girgensohn, Lynn Wilcox:
  Authoring, viewing, and generating hypervideo: An overview of Hyper-Hitchcock.

• Wenbo He, Klara Nahrstedt, Xue Liu:
  End-to-end delay control of multimedia applications over multihop wireless links.

• Leon Pan, Chang N. Zhang:
  A criterion-based multilayer access control approach for multimedia applications and the implementation considerations.