| IEICE Technical Committee Submission System Advance Program |
Online Proceedings [Sign in] Tech. Rep. Archives |
| Go Top | Go Back | Prev IBISML Conf / Next IBISML Conf | [HTML] / [HTML(simple)] / [TEXT] | [Japanese] / [English] |
|
=============================================== Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML) Chair: Kenji Yamanishi (Univ. of Tokyo) Vice Chair: Naonori Ueda (NTT), Tomoyuki Higuchi (ISM) Secretary: Masashi Sugiyama (Tokyo Inst. of Tech.), Tsuyoshi Ide (IBM) Assistant: Daichi Mochihashi (NTT), Shigeyuki Ohba (Kyoto Univ.) =============================================== Technical Committee on Pattern Recognition and Media Understanding (PRMU) Chair: Michihiko Mino (Kyoto Univ.) Vice Chair: Yoichi Sato (Univ. of Tokyo), Minoru Etoh (NTT DoCoMo) Secretary: Osamu Yamaguchi (Toshiba), Masayuki Kanbara (NAIST) Assistant: Toru Tamaki (Hiroshima Univ.), Hironobu Fujiyoshi (Chubu Univ.) DATE: Sun, Sep 5, 2010 09:00 - 18:00 Mon, Sep 6, 2010 09:00 - 17:30 PLACE: (http://www.fukuoka-u.ac.jp/unv_gide/access/index.html) TOPICS: Machine learning and optimization for computer vision and pattern recognition, etc. ---------------------------------------- Sun, Sep 5 AM (09:00 - 10:30) ---------------------------------------- (1)/PRMU 09:00 - 09:30 Behavior of kernel mutual subspace method with respect to parameters Seiji Hotta (TUAT), Tomokazu Kawahara, Osamu Yamaguchi (Toshiba Corp.), Hitoshi Sakano (NTT) (2)/PRMU 09:30 - 10:00 Multiple Kernel Learning for Generic Object Recognition Using SIFT Gaussian Mixture Models Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda, Sadaoki Furui (Tokyo Tech) (3)/PRMU 10:00 - 10:30 Generic Object Recognition Based on Rough Segmentation Data Given by a User Mitsuru Ambai, Yuichi Yoshida (Denso IT Laboratory, Inc.) ---------------------------------------- Sun, Sep 5 AM (09:00 - 10:30) ---------------------------------------- (4) 09:00 - 09:30 (5) 09:30 - 10:00 (6) 10:00 - 10:30 ----- Break ( 10 min. ) ----- ---------------------------------------- Sun, Sep 5 AM (10:40 - 12:10) ---------------------------------------- (7)/IBISML 10:40 - 11:10 Improving the Accuracy of Least-Squares Probabilistic Classifiers Makoto Yamada, Masashi Sugiyama (Tokyo Inst. of Tech.), Gordon Wichern (MIT Lincoln Lab), Jaak Simm (Tokyo Inst. of Tech.) (8)/IBISML 11:10 - 11:40 Multi-task Learning with Least-Squares Probabilistic Classifiers Jaak Simm, Masashi Sugiyama (Tokyo Inst. of Tech.), Tsuyoshi Kato (Univ. of Tokyo) (9)/IBISML 11:40 - 12:10 Computational identification of discriminating features of pathogenic and symbiotic Type III secreted effector proteins Koji Yahara, Ying Jiang, Takashi Yanagawa (Kurume Univ.) ---------------------------------------- Sun, Sep 5 AM (10:40 - 12:10) ---------------------------------------- (10)/PRMU 10:40 - 11:10 QR-code recognition based on super-resolution using binary pattern constraint Yuji Kato, Daisuke Deguchi (Nagoya Univ.), Tomokazu Takahashi (Gifu Shotoku Gakuen Univ.), Ichiro Ide, Hiroshi Murase (Nagoya Univ.) (11)/PRMU 11:10 - 11:40 Store-Shelf-Label Recognition Using Label-Element Detection and Model Matching Yasunori Doi, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo, Noboru Ohnishi (Nagoya Univ.) (12)/PRMU 11:40 - 12:10 Is quantity better than quality? -- A study case on a simple classifier applied to digit character recognition -- Sabine Barrat (Osaka Prefecture Univ./JSPS/Nancy Univ./LORIA), Geoffrey Alary (Osaka Prefecture Univ./EISTI), Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ.), Seiichi Uchida (Kyushu Univ.), Shinichiro Omachi (Tohoku Univ.) ----- Break ( 90 min. ) ----- ---------------------------------------- Sun, Sep 5 PM (13:40 - 14:40) ---------------------------------------- (13)/IBISML 13:40 - 14:40 [Special Talk] Pattern Mining meets a New Landing Point -- Pattern mining via clustering -- Takeaki Uno (NII) ----- Break ( 10 min. ) ----- ---------------------------------------- Sun, Sep 5 PM (14:50 - 15:50) ---------------------------------------- (14)/PRMU 14:50 - 15:50 [Special Talk] Higher-order optimization and learning in vision -- a bottom-up approach -- Hiroshi Ishikawa (Waseda Univ.) ----- Break ( 10 min. ) ----- ---------------------------------------- Sun, Sep 5 PM (16:00 - 18:00) ---------------------------------------- (15)/IBISML 16:00 - 16:30 Facial Expression Recognition by Ensemble Learning Using Movements of Facial Feature Points Hiroki Nomiya, Teruhisa Hochin (KIT) (16)/PRMU 16:30 - 17:00 Sound Source Detection by Learning Chihiro Ikeda, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) (17)/PRMU 17:00 - 17:30 Improvement in Human Detection by Generation Addition Training of Human Silhouette Naoya Kouketsu, Yuji Yamauchi, Hironobu Fujiyoshi (Chubu Univ.) (18)/IBISML 17:30 - 18:00 A Study on Feature Selection Path for High-Dimensional Local Classifiers Ichiro Takeuchi (NIT) ---------------------------------------- Sun, Sep 5 PM (16:00 - 17:30) ---------------------------------------- (19)/PRMU 16:00 - 16:30 Fast Template Matching Using Adaptive Block Partitioning and Threshold Estimation Minoru Mori, Junji Yamato (NTT) (20) 16:30 - 17:00 (21)/PRMU 17:00 - 17:30 Colorectal NBI Image Recognition using Dense SIFT Junki Yoshimuta, Takahishi Takeda, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Yoshito Takemura, Shigeto Yoshida, Shinji Tanaka (Hiroshima Univ.) ---------------------------------------- Mon, Sep 6 AM (09:00 - 10:30) ---------------------------------------- (22)/IBISML 09:00 - 09:30 A Study of Variances of Cross-Validation and Generalization Error in Variational Bayes Method Shinji Oyama, Sumio Watanabe (Tokyo Tech.) (23)/IBISML 09:30 - 10:00 Proposal of MCMC methods on hidden variables of a nomral mixture and its application to Bayes marginal Likelihood Takushi Miki, Sumio Watanabe (Tokyo Tech) (24)/IBISML 10:00 - 10:30 A Density Ratio Approach to Two-Sample Test Masashi Sugiyama (Tokyo Inst. of Tech.), Taiji Suzuki (Univ. of Tokyo), Yuta Itoh (Tokyo Inst. of Tech.), Takafumi Kanamori (Nagoya Univ.), Manabu Kimura (Tokyo Inst. of Tech.) ---------------------------------------- Mon, Sep 6 AM (09:00 - 10:30) ---------------------------------------- (25)/PRMU 09:00 - 09:30 Sequential Pattern Recognition by Local Classifiers and Dynamic Time Warping Masahiro Fukutomi, Koichi Ogawara, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) (26)/PRMU 09:30 - 10:00 Object Tracking by a Combination of Discrete DP and Analytical DP Hiroki Kawano, Ikko Fujimura, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) (27)/PRMU 10:00 - 10:30 Consistent Localization of Persons by Integrating Global and Local Observations Yuuki Chijiwa, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) ----- Break ( 10 min. ) ----- ---------------------------------------- Mon, Sep 6 AM (10:40 - 12:10) ---------------------------------------- (28)/PRMU 10:40 - 11:10 Minimum Classification Error Training with Automatic Control of Loss Smoothness Junichi Tokuno (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.) (29)/PRMU 11:10 - 11:40 Learning Vector Quantization Using a Heavy-tailed Distribution Ansatz Hiroyoshi Miyano, Eiki Ishidera (NEC Informatec Systems) (30)/IBISML 11:40 - 12:10 Evaluation of the error rate of the classifier under the margin assumption Takanori Ayano, Joe Suzuki (Osaka Univ) ---------------------------------------- Mon, Sep 6 AM (10:40 - 11:10) ---------------------------------------- (31)/PRMU 10:40 - 11:10 Action planning for interactive visual scene understanding based on knowledge confidence defined on latent spaces Gurbachan Sekhon (Univ. of British Columbia), Akisato Kimura, Yasuhiro Minami, Hitoshi Sakano, Eisaku Maeda (NTT) ----- Break ( 90 min. ) ----- ---------------------------------------- Mon, Sep 6 PM (13:40 - 14:40) ---------------------------------------- (32)/PRMU 13:40 - 14:40 [Fellow Memorial Lecture] - Takio Kurita (Hiroshima Univ.) ----- Break ( 10 min. ) ----- ---------------------------------------- Mon, Sep 6 PM (14:50 - 15:50) ---------------------------------------- (33)/PRMU 14:50 - 15:50 [Fellow Memorial Lecture] From the Subspace Method to the Mutual Subspace Method Ken-ichi Maeda (Toshiba Research/Toshiba) ----- Break ( 10 min. ) ----- ---------------------------------------- Mon, Sep 6 PM (16:00 - 17:00) ---------------------------------------- (34) 16:00 - 16:30 (35) 16:30 - 17:00 ---------------------------------------- Mon, Sep 6 PM (16:00 - 17:30) ---------------------------------------- (36)/PRMU 16:00 - 16:30 q-normal distribution and its escort distribution -- What is an escort distribution? -- Masaru Tanaka (Fukuoka Univ.) (37)/PRMU 16:30 - 17:00 General Scheme of Continuous Dynamic Programming -- Optimal Full Pixel Matching for Spotting Image -- Ryuichi Oka, Yuichi Yaguchi, Shinya Nizoe (Aizu Univ) (38) 17:00 - 17:30 # Information for speakers General Talk will have 20 minutes for presentation and 10 minutes for discussion. === Technical Committee on Infomation-Based Induction Sciences and Machine Learning (IBISML) === # FUTURE SCHEDULE: Thu, Nov 4, 2010 - Sat, Nov 6, 2010: IIS, Univ. of Tokyo [Fri, Sep 17], Topics: IBIS 2010 (Workshop on Information-based Induction Sciences) === Technical Committee on Pattern Recognition and Media Understanding (PRMU) === # FUTURE SCHEDULE: Fri, Oct 8, 2010 - Sat, Oct 9, 2010: [Tue, Jul 20] Thu, Nov 18, 2010 - Fri, Nov 19, 2010: [Mon, Sep 6] Thu, Dec 9, 2010 - Fri, Dec 10, 2010: [Fri, Oct 8] # SECRETARY: Contact address: pr  - n    Last modified: 2010-09-04 20:12:13 |
Notification: Mail addresses are partially hidden against SPAM.
[Download Paper's Information (in Japanese)] <-- Press download button after click here.
[Cover and Index of IEICE Technical Report by Issue]
[Presentation and Participation FAQ] (in Japanese)
[Return to PRMU Schedule Page] / [Return to IBISML Schedule Page] /
| Go Top | Go Back | Prev IBISML Conf / Next IBISML Conf | [HTML] / [HTML(simple)] / [TEXT] | [Japanese] / [English] |
[Return to Top Page]