| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| PRMU |
2005-12-15
13:00 |
Niigata |
Niigata Univ. |
Dance from Music based on Choreographic Examples
Hiroyuki Aozuka, Masanobu Yamamoto (Niigata U.) |
Relating an action and a sound synchronized each other, one can produce a new action according to a new sound by the rel... [more] |
PRMU2005-123
pp.1-6 |
| PRMU |
2005-12-15
13:30 |
Niigata |
Niigata Univ. |
A Comparison between a Local Feature and a Global Feature for Identical Video Segment Detection
Fuminori Yamagishi (Univ. Tokyo), Shin'ichi Satoh (NII), Alexis Joly (INRIA), Olivier Buisson (INA), Nozha Boujemaa (INRIA), Masao Sakauchi (NII) |
Some kind of video footage is repeatedly used in a video archive. Identical Video Segment Deteciton, which is a detectio... [more] |
PRMU2005-124
pp.7-11 |
| PRMU |
2005-12-15
14:00 |
Niigata |
Niigata Univ. |
A Weighted Voting Method for Combining Multiple Character Recognition Engines
Shoichiro Kaneko, Hideaki Goto, Hiroaki Kobayashi (Tohoku Univ.) |
多数決原理，複数文字認識エンジン，信頼度重み [more] |
PRMU2005-125
pp.13-18 |
| PRMU |
2005-12-15
14:45 |
Niigata |
Niigata Univ. |
[Special Talk]
My Way of Building Human Network
-- Merits of Utilizing Chances and Demerits of Being in Multiple Disciplines --
Yoshiaki Shirai (Ritsumeikan Univ.) |
I have been involved in various organizatios related to my fields, which helped me in making human networks. Especially,... [more] |
PRMU2005-126
pp.19-24 |
| PRMU |
2005-12-15
15:45 |
Niigata |
Niigata Univ. |
[Special Talk]
-
-- - --
Masakazu Ejiri |
As a researcher in industry, the author has long been engaged in the creation of machine vision technology and the promo... [more] |
PRMU2005-127
pp.25-32 |
| PRMU |
2005-12-16
10:00 |
Niigata |
Niigata Univ. |
[Tutorial Lecture]
Auditory scene analysis and speech perception
-- A magical function for enabling speech communications in a world full of sounds --
Hideki Kawahara (Wakayama Univ.) |
We are living in a world full of sounds. In few situations, there exists only talker's speech sound in conversation. How... [more] |
PRMU2005-128
pp.1-6 |
| PRMU |
2005-12-16
11:00 |
Niigata |
Niigata Univ. |
[Tutorial Lecture]
Corpus based approaches for speech processing
Kazuya Takeda (Nagoya Univ.) |
Statistical approaches for modeling and training Spoken Language Systems (SLS) using large speech corpora have improved ... [more] |
PRMU2005-129
pp.7-12 |
| PRMU |
2005-12-16
13:00 |
Niigata |
Niigata Univ. |
Adaptive Subspace Splitting Using Minimum-Description-Length-Principles for Efficient Boosting
Duy-Dinh Le (Sokendai), Shin'ichi Satoh (NII) |
In RealBoost learning, selecting best weak classifiers is one of the most significant tasks. Generally, it is done accor... [more] |
PRMU2005-130
pp.13-18 |
| PRMU |
2005-12-16
13:30 |
Niigata |
Niigata Univ. |
N-Point Hough Transform derived by Geomtric Duality
Yoshihiko Mochizuki, Akihiko Torii, Atsushi Imiya (Chiba Univ.) |
[more] |
PRMU2005-131
pp.19-24 |
| PRMU |
2005-12-16
14:00 |
Niigata |
Niigata Univ. |
Hough Transform for Spherical Images
Akihiko Torii, Yoshihiko Mochizuki, Atsushi Imiya (Chiba Univ.) |
[more] |
PRMU2005-132
pp.25-30 |
| PRMU |
2005-12-16
14:45 |
Niigata |
Niigata Univ. |
Deep Structure of Morphological Scale Space
Atsushi Imiya, Tomoya Sakai (Chiba Univ.) |
[more] |
PRMU2005-133
pp.31-36 |
| PRMU |
2005-12-16
15:15 |
Niigata |
Niigata Univ. |
A Multicamera Stereo Method with Occlusion Handling
Satoshi Odakura, Toru Abe, Tetsuo Kinoshita (Tohoku Univ.) |
Multicamera stereo methods, which use more than two cameras and employ
multiple pairs of images, have been proposed a... [more] |
PRMU2005-134
pp.37-42 |
| PRMU |
2005-12-16
15:45 |
Niigata |
Niigata Univ. |
Theoretical and experimental evaluation of optical flow detection methods based on modulated imaging
Paul Masurel, Dabi Wei, Toru Kurihara, Shigeru Ando (Univ. of Tokyo) |
[more] |
PRMU2005-135
pp.43-48 |