Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, NLC |
2005-02-24 09:30 |
Tokyo |
|
Biological network inference via kernel matrix completion Tsuyoshi Kato (AIST), Koji Tsuda (AIST/MPI for Biologcal Cybernetics), Kiyoshi Asai (Univ. of Tokyo/AIST) |
Inferring networks of proteins from biological data is a central issue of computational biology. Most network inference ... [more] |
NLC2004-97 PRMU2004-179 pp.1-6 |
PRMU, NLC |
2005-02-24 10:00 |
Tokyo |
|
Space Partitioning Method for Classifier Selection Hiromu Hayashi, Takayuki Nakamura, Toshikazu Wada (Wakayama Univ.) |
Ensemble learing is a method for constructing a strong
crassifier from multiple weak classifiers. In this method,
the ... [more] |
NLC2004-98 PRMU2004-180 pp.7-12 |
PRMU, NLC |
2005-02-24 10:30 |
Tokyo |
|
MDL-based nonlinear regression tree Yoshimi Uezu, Takayuki Nakamura, Toshikazu Wada (Wakayama Univ.) |
In the previous work, we proposed the ''\ PaLM-Tree '' which is a kind of linear regression tree. It improves some drawb... [more] |
NLC2004-99 PRMU2004-181 pp.13-18 |
PRMU, NLC |
2005-02-24 11:00 |
Tokyo |
|
Optimal combination of labeled and unlabeled data for semi-supervised classification Akinori Fujino, Naonori Ueda, Kazumi Saito (NTT) |
Unlabeled data are used to improve the accuracy of classifiers when the number of labeled data is not enough. In probabi... [more] |
NLC2004-100 PRMU2004-182 pp.19-24 |
PRMU, NLC |
2005-02-24 11:30 |
Tokyo |
|
Theory and application for semi-supervised learning Naonori Ueda (NTT) |
[more] |
NLC2004-101 PRMU2004-183 pp.25-30 |
PRMU, NLC |
2005-02-24 13:00 |
Tokyo |
|
Estimation of shaking background from videos using online realtime PCA Kenji Sugiyama, Hisashi Koga, Toshinori Watanabe, Takanori Yokoyama (UEC) |
In this paper, we proposed the technique which presumes the background from the movie affected by the background change ... [more] |
NLC2004-102 PRMU2004-184 pp.31-36 |
PRMU, NLC |
2005-02-24 13:30 |
Tokyo |
|
Automatical Extraction of Object-tracks from Videos using LSH-Link Clustering Algorithm Hiroaki Kusaba, Hisashi Koga, Toshinori Watanabe (UEC) |
This paper proposes a non-parametric simple algorithm to extract objects from the spatio-temporal region.
Our algorithm... [more] |
NLC2004-103 PRMU2004-185 pp.37-42 |
PRMU, NLC |
2005-02-24 14:00 |
Tokyo |
|
Probabilistic estimation of pedestrian routes over non-overlapping views Yukihisa Ikegame, Makoto Hirano, Touru Tamaki, Masanobu Yamamoto (Niigata Univ.) |
In this research we propose the method of probabilistic estimation of
pedestrian routes over non-overlapping views for... [more] |
NLC2004-104 PRMU2004-186 pp.43-48 |
PRMU, NLC |
2005-02-24 14:30 |
Tokyo |
|
Pedestrian Detection by Boosting Soft-Margin SVM with Feature Selection Kenji Nishida, Takio Kurita (AIST) |
[more] |
NLC2004-105 PRMU2004-187 pp.49-54 |
PRMU, NLC |
2005-02-24 13:00 |
Tokyo |
|
Extraction of Natural Quadric Surfaces from Range Image Using Hough Transform and EM Algorithm Kokushi Yamamoto, Atsushi Nakazawa, Kiyoshi Kiyokawa, Haruo Takemura (Osaka Univ.) |
[more] |
NLC2004-106 PRMU2004-188 pp.55-60 |
PRMU, NLC |
2005-02-24 13:30 |
Tokyo |
|
Non-linear diffusion filtering derived from the deep structure analysis in scale space Haruhiko Nishiguchi, Atsushi Imiya, Tomoya Sakai (Chiba Univ.) |
[more] |
NLC2004-107 PRMU2004-189 pp.61-66 |
PRMU, NLC |
2005-02-24 14:00 |
Tokyo |
|
Navigation from optical flow Naoya Ohnishi, Atsushi Imiya (Chiba Univ.) |
In this paper, we aim to develop an algorithm for navigation of an autonomous mobile robot using optical flow observed t... [more] |
NLC2004-108 PRMU2004-190 pp.67-72 |
PRMU, NLC |
2005-02-24 14:30 |
Tokyo |
|
Human Extraction Using Optical Flow in Complex Background Toshiki Iwasaki, Takanori Yokoyama, Hisashi Koga, Toshinori Watanabe (UEC) |
[more] |
NLC2004-109 PRMU2004-191 pp.73-77 |
PRMU, NLC |
2005-02-24 15:10 |
Tokyo |
|
Elimination of string obstacles and image restoration Hiroshi Suzuki, Toru Tamaki, Masanobu Yamamoto (Niigata Univ.) |
In this paper, we propose a technique for extracting and
eliminating obstacles in a still image. We assume that the
... [more] |
NLC2004-110 PRMU2004-192 pp.79-84 |
PRMU, NLC |
2005-02-24 15:40 |
Tokyo |
|
Estimating Texrure Plane Orientation With Fractal Image Encoding Keiji Shintaku, Toshikazu Wada, Haiyuan Wu (Wakayama Univ.) |
Fractal coding is based on the assumption of self-affinity. In image coding, blocks of an image can be approximated by e... [more] |
NLC2004-111 PRMU2004-193 pp.85-90 |
PRMU, NLC |
2005-02-24 16:10 |
Tokyo |
|
An approach to real-time gesture recognition for human-PC Yohei Sato, Kokichi Sugihara (Tokyo Univ.) |
Hand gesture recognition is one of the most important researches
for Human-computer interaction, and this paper presen... [more] |
NLC2004-112 PRMU2004-194 pp.91-96 |
PRMU, NLC |
2005-02-24 15:10 |
Tokyo |
|
Merging Shock Trees Using Alignable Mappings Tetsuji Kuboyama, Kilho Shin (Univ. of Tokyo), Tetsuhiro Miyahara (Hiroshima City Univ.) |
A shock tree is a very effective characterization for representing 2D shapes. Torsello and Hancock have proposed an unsu... [more] |
NLC2004-113 PRMU2004-195 pp.97-102 |
PRMU, NLC |
2005-02-24 15:40 |
Tokyo |
|
Consideration of Similarities between DTDs using Dynamic Programming Matching of Trees Takuya Onozato, Hisashi Koga, Toshinori Watanabe (UEC) |
Tree structure is useful for representing various objects such as XML and
gene data. To retrieve and classify objects d... [more] |
NLC2004-114 PRMU2004-196 pp.103-108 |
PRMU, NLC |
2005-02-24 16:10 |
Tokyo |
|
Realtime Human Action Recognition using High Speed Calculation of Subgraph Similarity in Feature Space Hiroki Shimono, Masami Satou, Hitoshi Kitazawa (TUAT) |
An extension of human action detection by the similarity of subgraphs which represent action templates and measurement i... [more] |
NLC2004-115 PRMU2004-197 pp.109-114 |
PRMU, NLC |
2005-02-25 10:00 |
Tokyo |
|
An Image Retrieval System of Flowers and Evaluation of its Retrieval Methods Soutarou Tabata, Kei Iwasaki, Saeko Takagi, Fujiichi Yoshimoto (Wakayama Univ.) |
Although there are many information retrieval systems, few systems can be used in mobile environments. In this paper, we... [more] |
NLC2004-116 PRMU2004-198 pp.1-6 |