Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 09:00 |
Fukuoka |
Fukuoka Univ. |
Behavior of kernel mutual subspace method with respect to parameters Seiji Hotta (TUAT), Tomokazu Kawahara, Osamu Yamaguchi (Toshiba Corp.), Hitoshi Sakano (NTT) PRMU2010-57 IBISML2010-29 |
Optimizing parameters of kernel methods is an unsolved problem. We report the experimental evaluation and the considerat... [more] |
PRMU2010-57 IBISML2010-29 pp.1-6 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 09:30 |
Fukuoka |
Fukuoka Univ. |
Multiple Kernel Learning for Generic Object Recognition Using SIFT Gaussian Mixture Models Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda, Sadaoki Furui (Tokyo Tech) PRMU2010-58 IBISML2010-30 |
We propose a statistical framework for generic object recognition using SIFT Gaussian mixture models (GMMs) and multiple... [more] |
PRMU2010-58 IBISML2010-30 pp.7-12 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 10:00 |
Fukuoka |
Fukuoka Univ. |
Generic Object Recognition Based on Rough Segmentation Data Given by a User Mitsuru Ambai, Yuichi Yoshida (Denso IT Laboratory, Inc.) PRMU2010-59 IBISML2010-31 |
In this paper, we revisit a generic object recognition problem from a point of view of human-computer interaction. Many ... [more] |
PRMU2010-59 IBISML2010-31 pp.13-20 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 10:40 |
Fukuoka |
Fukuoka Univ. |
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.) PRMU2010-60 IBISML2010-32 |
Least-Squares Probabilistic Classifier (LSPC) has been demonstrated to be a computationally-efficient and accurate class... [more] |
PRMU2010-60 IBISML2010-32 pp.45-50 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 11:10 |
Fukuoka |
Fukuoka Univ. |
Multi-task Learning with Least-Squares Probabilistic Classifiers Jaak Simm, Masashi Sugiyama (Tokyo Inst. of Tech.), Tsuyoshi Kato (Univ. of Tokyo) PRMU2010-61 IBISML2010-33 |
Probabilistic classification and multi-task learning are two important
branches of machine learning research.
Probabil... [more] |
PRMU2010-61 IBISML2010-33 pp.51-56 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 11:40 |
Fukuoka |
Fukuoka Univ. |
Computational identification of discriminating features of pathogenic and symbiotic Type III secreted effector proteins Koji Yahara, Ying Jiang, Takashi Yanagawa (Kurume Univ.) PRMU2010-62 IBISML2010-34 |
Type III secretion systems (T3SS) deliver bacterial proteins, or "effectors", into eukaryotic host cells, inducing physi... [more] |
PRMU2010-62 IBISML2010-34 pp.57-62 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 10:40 |
Fukuoka |
Fukuoka Univ. |
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.) PRMU2010-63 IBISML2010-35 |
(Advance abstract in Japanese is available) [more] |
PRMU2010-63 IBISML2010-35 pp.63-68 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 11:10 |
Fukuoka |
Fukuoka Univ. |
Store-Shelf-Label Recognition Using Label-Element Detection and Model Matching Yasunori Doi, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo, Noboru Ohnishi (Nagoya Univ.) PRMU2010-64 IBISML2010-36 |
There are some problems of store-shelf-label recognition: (1)a variety of label types, (2)complex background, (3)rotatio... [more] |
PRMU2010-64 IBISML2010-36 pp.69-74 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 11:40 |
Fukuoka |
Fukuoka Univ. |
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.) PRMU2010-65 IBISML2010-37 |
This paper deals with a learning method for digit character recognition.
We propose to expand character image databases... [more] |
PRMU2010-65 IBISML2010-37 pp.75-80 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 13:40 |
Fukuoka |
Fukuoka Univ. |
[Special Talk]
Pattern Mining meets a New Landing Point
-- Pattern mining via clustering -- Takeaki Uno (NII) PRMU2010-66 IBISML2010-38 |
Pattern mining has a disadvantage that huge amount of similar patterns are detected. There are many researches address t... [more] |
PRMU2010-66 IBISML2010-38 pp.81-82 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 14:50 |
Fukuoka |
Fukuoka Univ. |
[Special Talk]
Higher-order optimization and learning in vision
-- a bottom-up approach -- Hiroshi Ishikawa (Waseda Univ.) PRMU2010-67 IBISML2010-39 |
Energy minimization methods such as those utilizing Markov Random Field (MRF) have come to be widely used in computer vi... [more] |
PRMU2010-67 IBISML2010-39 p.83 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 16:00 |
Fukuoka |
Fukuoka Univ. |
Facial Expression Recognition by Ensemble Learning Using Movements of Facial Feature Points Hiroki Nomiya, Teruhisa Hochin (KIT) PRMU2010-68 IBISML2010-40 |
We propose a facial expression recognition method using several facial feature points such as end points and centroids o... [more] |
PRMU2010-68 IBISML2010-40 pp.85-92 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 16:30 |
Fukuoka |
Fukuoka Univ. |
Sound Source Detection by Learning Chihiro Ikeda, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) PRMU2010-69 IBISML2010-41 |
Sound source detection in an image is a difficult inverse problem where the pixels belonging to the sound source area ar... [more] |
PRMU2010-69 IBISML2010-41 pp.93-98 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 17:00 |
Fukuoka |
Fukuoka Univ. |
Improvement in Human Detection by Generation Addition Training of Human Silhouette Naoya Kouketsu, Yuji Yamauchi, Hironobu Fujiyoshi (Chubu Univ.) PRMU2010-70 IBISML2010-42 |
An object detection method that involves additional learning with a training sample generated by a 3-D human model is pr... [more] |
PRMU2010-70 IBISML2010-42 pp.99-104 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 17:30 |
Fukuoka |
Fukuoka Univ. |
A Study on Feature Selection Path for High-Dimensional Local Classifiers Ichiro Takeuchi (NIT) PRMU2010-71 IBISML2010-43 |
We study feature selection and weighting problems for local-based classifier. The proposed algorithm is formulated as a ... [more] |
PRMU2010-71 IBISML2010-43 pp.105-112 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 16:00 |
Fukuoka |
Fukuoka Univ. |
Fast Template Matching Using Adaptive Block Partitioning and Threshold Estimation Minoru Mori, Junji Yamato (NTT) PRMU2010-72 IBISML2010-44 |
This paper proposes a fast method that reduces the computation cost of template matching. We extend the Multilevel Succe... [more] |
PRMU2010-72 IBISML2010-44 pp.113-120 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 17:00 |
Fukuoka |
Fukuoka Univ. |
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.) PRMU2010-73 IBISML2010-45 |
In this paper we propose a recognition system for classifying NBI images of colorectal tumors into three types (A, B, an... [more] |
PRMU2010-73 IBISML2010-45 pp.129-134 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 09:00 |
Fukuoka |
Fukuoka Univ. |
A Study of Variances of Cross-Validation and Generalization Error in Variational Bayes Method Shinji Oyama, Sumio Watanabe (Tokyo Tech.) PRMU2010-74 IBISML2010-46 |
Variational Bayes method provides high generalization performance as the Bayes method using a small computational cost a... [more] |
PRMU2010-74 IBISML2010-46 pp.135-142 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 09:30 |
Fukuoka |
Fukuoka Univ. |
Proposal of MCMC methods on hidden variables of a nomral mixture and its application to Bayes marginal Likelihood Takushi Miki, Sumio Watanabe (Tokyo Tech) PRMU2010-75 IBISML2010-47 |
The Bayes marginal likelihood has important information for model
selection, optimization for hyperparameter.However, ... [more] |
PRMU2010-75 IBISML2010-47 pp.143-148 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 10:00 |
Fukuoka |
Fukuoka Univ. |
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.) PRMU2010-76 IBISML2010-48 |
The goal of the two-sample test (a.k.a. the homogeneity test)
is, given two sets of samples, to judge whether
the prob... [more] |
PRMU2010-76 IBISML2010-48 pp.149-156 |