Thu, Feb 17 AM 10:00 - 11:30 |
(1) |
10:00-10:30 |
Large Scale Image Classification using Metric based on Correlation between Multiple Image Features and Class Labels |
Yoshitaka Ushiku, Yuya Yamashita, Jun Imura, Hideki Nakayama, Tatsuya Harada, Yasuo Kuniyoshi (Tokyo Univ.) |
(2) |
10:30-11:00 |
Automatic Image Annotation by Variational Random Forests |
Motofumi Fukui, Noriji Kato, Qi Wenyuan (Fuji Xerox) |
(3) |
11:00-11:30 |
An Extension of Semantic Texton Forests to Multi-Label Problem Using Label Ranking |
Takaaki Fukuta, Hironobu Fujiyoshi (Chubu Univ.) |
|
11:30-13:00 |
Lunch Break ( 90 min. ) |
Thu, Feb 17 PM 13:00 - 15:20 |
(4) |
13:00-13:50 |
[Special Talk]
An overview of video analysis and retrieval evaluation workshop TRECVID2010 |
Shin'ichi Satoh (NII), Koichi Shinoda (TITECH) |
(5) |
13:50-14:20 |
A Multi-modal, Multi-frame Approach for Semantic Indexing in TRECVID |
Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda (Tokyo Tech) |
(6) |
14:20-14:50 |
Approach to conbine Bag-of-Frames and spatio temporal features for TRECVID2010 Semantic Indexing Task |
Yasushi Shimoda, Akitsugu Noguchi, Keiji Yanai (UEC) |
(7) |
14:50-15:20 |
An analytical method of semantic content for a large amount of video archive |
Yoshihiko Kawai, Mahito Fujii (NHK) |
|
15:20-15:30 |
Break ( 10 min. ) |
Thu, Feb 17 PM 15:30 - 17:00 |
(8) |
15:30-16:00 |
Video Similarity Measuring using SIFT Trajectories without Pre-learning Process |
Hiroaki Kubo, Hideo Saito (Keio Univ.), Shin'ichi Satoh (NII) |
(9) |
16:00-16:30 |
Accurate Content-Based Copy Detection Scheme Using Global/Local Visual Features and Audio Features |
Yusuke Uchida, Shigeyuki Sakazawa (KDDI Labs) |
(10) |
16:30-17:00 |
A Report on the TRECVID 2010 Content-Based Copy Detection Task |
Ryo Mukai, Takayuki Kurozumi, Kaoru Hiramatsu, Takahito Kawanishi, Hidehisa Nagano, Kunio Kashino (NTT) |
|
17:00-17:10 |
Break ( 10 min. ) |
Thu, Feb 17 PM 17:10 - 18:00 |
(11) |
17:10-18:00 |
[Special Talk]
Large-Scale Generic Image Recognition and Image Representation |
Tatsuya Harada (The Univ. of Tokyo) |
Fri, Feb 18 AM 10:00 - 11:30 |
(12) |
10:00-10:30 |
Baseline Approach for Instance Search Task: Local Region-based Face Matching and Regional Combination of Local Features |
Duy-Dinh Le, Sebastien Poullot, Shin'ichi Satoh (NII) |
(13) |
10:30-11:00 |
A Report on the TRECVID 2010 Instance Search Task |
Takahito Kawanishi, Akisato Kimura, Kunio Kashino (NTT), Shin'ichi Satoh, Duy-Dinh Le, Xiaomeng Wu, Sebastien Poullot (NII) |
(14) |
11:00-11:30 |
Event Detection by Multiple Keyframes Extraction Based on Scene Length
-- Nikon Multimedia Event Detection System -- |
Takeshi Matsuo, Shinichi Nakajima (Nikon) |
Fri, Feb 18 AM 10:00 - 11:30 |
(15) |
10:00-10:30 |
Adult recognition Method using Biometrics
-- Water Retention Characteristics Detection Using Near Infrared Ray Spectral Characteristic of Cheek -- |
Satoshi Nishino, Shun Yasuda (ONCT) |
(16) |
10:30-11:00 |
Partial Matching Method using Spatio-temporal Regularized Canonical Correlation Analysis |
Yoshiaki Kodama (Univ. Tsukuba), Takumi Kobayashi, Nobuyuki Otsu (AIST), Kazuhiro Fukui (Univ. Tsukuba) |
(17) |
11:00-11:30 |
An Estimation Method of Position from an Omnidirectional Image for a Two-leg Walking Robot |
Toshihiko Kanbara, Yuuichirou Numasawa, Hidehiro Seki (Hachinohe Inst. Tech.) |
|
11:30-13:00 |
Lunch Break ( 90 min. ) |
Fri, Feb 18 PM 13:00 - 15:00 |
(18) |
13:00-13:30 |
Human motion recognition in crowded surveillance video sequences based on key-point trajectories |
Masaki Takahashi, Mahito Fujii, Masahide Naemura (NHKSTRL), Shin'ichi Satoh (NII) |
(19) |
13:30-14:00 |
Performance comparison of the hashing retrieval method for the large-scale video data |
Noboru Murabayashi, Kenichi Yoshida (Univ. of Tsukuba) |
(20) |
14:00-14:30 |
Negative Selection for High Dimensional Feature in Video Retrieval with Query-by-Example Method |
Yuta Matsuoka, Kimiaki Shirahama, Kuniaki Uehara (Kobe Univ.) |
(21) |
14:30-15:00 |
Retrieving a Large Variety of Videos from a Small Number of Example Videos based on Rough Set Theory |
Kimiaki Shirahama, Yuta Matsuoka, Kuniaki Uehara (Kobe Univ.) |
Fri, Feb 18 PM 13:00 - 15:00 |
(22) |
13:00-13:30 |
Human attribute analysis using a ceiling camera in a public space |
Tomoaki Matsunami, Toshihiko Yamasaki, Kiyoharu Aizawa (The Univ. of Tokyo) |
(23) |
13:30-14:00 |
A Study of Human Motion Recognition Based on Tensor Decomposition using a Multiple Viewpoint Image Sequence |
Takayuki Hori, Jun Ohya (Waseda Univ.), Jun Kurumisawa (CUC) |
(24) |
14:00-14:30 |
Evaluation for Multi-View Images Based on Quality-of-View |
Yuki Nagai, Takafumi Marutani, Shoji Kajita, Kenji Mase (Nagoya Univ.) |
(25) |
14:30-15:00 |
Probabilistic Background Texture Modeling for Object Detection |
Satoshi Yoshinaga, Atsushi Shimada, Hajime Nagahara, Rin-ichiro Taniguchi (Kyushu Univ.) |
|
15:00-15:10 |
Break ( 10 min. ) |
Fri, Feb 18 PM 15:10 - 16:10 |
(26) |
15:10-15:40 |
Mining Specific Actions from Youtube Video with Spatio-Temporal Features |
Do Hang Nga, Keiji Yanai (UEC) |
(27) |
15:40-16:10 |
News Shot Cloud: Listing TV News Shots with Estimating Their Visual Usefulness from the Number of Appearing Channels |
Norio Katayama, Hiroshi Mo, Shin'ichi Satoh (NII) |
Fri, Feb 18 PM 15:10 - 16:10 |
(28) |
15:10-15:40 |
A Motion Estimation Using Frenet Frame |
Kentaro Sako, Mitsuhiko Fujio (K.I.T) |
(29) |
15:40-16:10 |
A study for segmentation method of buildings from bird's eye view and streetscape images based on regular patterns in buildings |
Satoshi Ueno, Shigeyuki Sakazawa (KDDI Labs.) |