------------------------------------------------------------------------ IEEE First Workshop on Emergent Issues in Large Amounts of Visual Data (WS-LAVD 2009) in conjunction with ICCV2009 October 4, 2009 in Kyoto, Japan http://www.lavd.org/ ======================================================================== Today, immensely large amounts of visual data are captured and recorded every moment. Also, we can download almost an infinite number of images and videos from the Internet, where the stored visual data are explosively increasing. << Can the Large Amount of Visual Aata Produce Something New? >> According to the idea of "quantity breeds quality", researchers are trying to find out new phenomena and their applications on the large amounts of visual data. "Generic object recognition", "Hallucination", "Irregularity detection", and "Cascaded ADA Boosting" are the successful examples. We already have these applications; however, they can be extended further. << Arm Ourselves for Fighting with the Monster! >> Through these researches, we noticed that most algorithms performing search, clustering, regression, and classification proposed so far lose effect on a large amount of visual data. This implies that more scalable algorithms and architectures have to be developed. For example, compact and powerful feature descriptors, memory efficient algorithms, distributed parallel architectures, and so on. << We Need Metallurgy for Making Strong Armor. >> For utilizing the visual data, label data are necessary in many cases. However, labeling is always expensive and available labels are often noisy. How can we make robust algorithms against such noisy labels? Also, an imbalanced training set may introduce bias into classifiers. How can we remove it? WE WANT TO HAVE A WORKSHOP FOR SOLVING THESE PROBLEMS! TOPICS-OF-INTEREST Paper submissions should be related but not limited to any of the following topics: << Scalable architectures for large amounts of visual data >> Cooperative Distributed Parallel systems, Multi-Agent systems, Parallel implementations of algorithms, and so on. << Scalable algorithms on large amounts of visual data >> Compact and powerful feature descriptors, Memory efficient scalable algorithms, External algorithms on HDD, Chunking, Serialization, and so on. << Applications exploiting large amounts of visual data >> Any applications using large amounts of visual data, such as Computational Photography using large amounts of images (Super-resolution, Automatic Colorization, etc), Irregularity Detection, Generic or specific object recognition, and so on. << Data collection and labeling >> Semi-supervised learning, Effortless labeling framework, Web crawler, and so on. SUBMISSION The authors are requested to prepare their papers following the ICCV2009 main conference instructions. See the following URL for details: http://www.iccv2009.org/submission/ All submitted papers are reviewed by at least two reviewers in a double-blind manner. It is our policy that duplicate submissions to this workshop are allowed only if the papers are primarily submitted to the main conference. Papers accepted to the main conference are alternatively not accepted to the workshop. IMPORTANT DATES Paper submission deadline June 15th, 2009 Paper acceptance notification July 25th, 2009 Camera ready submission deadline Aug. 10th, 2009 Workshop Oct. 4th, 2009 ORGANIZATION General chair Toshikazu Wada Wakayama Univ., JP Program chairs Koichi Kise Osaka Prefecture Univ., JP Shin'ichi Satoh National Institute of Informatics, JP Publication chair Takahiro Okabe The Univ. of Tokyo, JP Web chairs Tatsuya Harada The Univ. of Tokyo, JP Keiji Yanai The Univ. of Electro-Communications, JP Publicity chair Ichiro Ide Nagoya University / NII, JP PC MEMBERS Kobus Barnard Univ. of Arizona, US Edward Chang Google, US Minoru Etoh NTT DoCoMo, JP Tatsuya Harada The Univ. of Tokyo, JP Ichiro Ide Nagoya University / NII, JP Frederic Jurie Univ. of Caen, FR Koichi Kise Osaka Prefecture Univ., JP Li Fei-Fei Princeton Univ., US Tao Mei Microsoft Research Asia, CN Chong-Wah Ngo City Univ. of Hong Kong, HK Takahiro Okabe The Univ. of Tokyo, JP Shin'ichi Satoh National Institute of Informatics, JP Cordelia Schmid INRIA, FR Josef Sivic INRIA, FR Cees Snoek Univ. of Amsterdam, NL Toshikazu Wada Wakayama Univ., JP Haiyuan Wu Wakayama Univ., JP Keiji Yanai The Univ. of Electro-Communications, JP CONTACT chairs@lavd.org