| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| PRMU |
2004-10-21
11:00 |
Hiroshima |
|
Video shooting navigation system by real-time useful shot discrimination on video grammar
Masahito Kumano (Ryukoku Univ.), Miki Amano (DoCoMo Kansai), Yasuo Ariki, Kuniaki Uehara (Kobe Univ.) |
In this paper, we propose a video shooting navigation system by real-time useful shot discrimination based on video gram... [more] |
PRMU2004-83
pp.1-6 |
| PRMU |
2004-10-21
11:30 |
Hiroshima |
|
User Interface for Automatic Video Editing based on Speaker's Intention
Motoyuki Ozeki (Univ. of Tsukuba), Yuichi Nakamura (Kyoto Univ.), Yuichi Ohta (Univ. of Tsukuba) |
In this paper, we investigate a user interface for automatic video editing based on speaker's intention through our vide... [more] |
PRMU2004-84
pp.7-12 |
| PRMU |
2004-10-21
12:00 |
Hiroshima |
|
Video-Based Media for Gently Giving Instructions
-- Object change detection and working process identification --
Yosuke Tsubuku, Takuya Kosaka, Yoshinari Kameda (Univ. of Tsukuba), Yuichi Nakamura (Kyoto Univ.), Yuichi Ohta (Univ. of Tsukuba) |
[more] |
PRMU2004-85
pp.13-18 |
| PRMU |
2004-10-21
13:30 |
Hiroshima |
|
[Special Talk]
Towards Structural Analysis of Instruction Video
Sadao Kurohashi, Tomohide Shibata (Tokyo Univ.) |
In realizing flexible utilization/access of real-word information or video contents, the crucial point is the structural... [more] |
PRMU2004-86
pp.19-23 |
| PRMU |
2004-10-21
14:40 |
Hiroshima |
|
Scripting TV Drama based on Viewer Dialogue
-- Analysis of Viewers' Attention on an Internet Bulletin Board --
Hiroshi Uehara, Kenichi Yoshida (Tsukuba Univ.) |
The rapidly expanding capacity of local storage such as hard disk
recorders is expected to create the need for a mechan... [more] |
PRMU2004-87
pp.25-30 |
| PRMU |
2004-10-21
15:10 |
Hiroshima |
|
Automatic Parsing of American Football Videos by Intermodal Collaboration
Naoko Nitta, Noboru Babaguchi (Osaka Univ.), Shih-Fu Chang (Columbia Univ.) |
This paper proposes a method of automatic parsing of American football
videos based on rules about the flows of an Ame... [more] |
PRMU2004-88
pp.31-36 |
| PRMU |
2004-10-21
15:40 |
Hiroshima |
|
Kanji Recognition in Scene Images without Detection of Text Fields for Indexing
-- Deduction of Calculation using Hierarchical Recognition Dictionaries --
Yoshinori Kusachi (NTT), Naomi Ito (NTT EAST), Akira Suzuki, Kenichi Arakawa (NTT) |
[more] |
PRMU2004-89
pp.37-42 |
| PRMU |
2004-10-22
10:30 |
Hiroshima |
|
Image thresholding by histogram segmentation using cluster organization avoiding local minima
Agus Zainal Arifin, Akira Asano (Hiroshima Univ.) |
Image thresholding is usually used to distinguish the foreground from the background. The image thresholding problem is ... [more] |
PRMU2004-90
pp.1-7 |
| PRMU |
2004-10-22
11:00 |
Hiroshima |
|
Pose Estimation of 3D Object Using Support Vector Regression
Shingo Ando, Yoshinori Kusachi, Akira Suzuki, Kenichi Arakawa (NTT) |
Several methods for estimating the pose of a 3D object from its appearance have been proposed. The parametric eigenspace... [more] |
PRMU2004-91
pp.9-15 |
| PRMU |
2004-10-22
11:30 |
Hiroshima |
|
Inter-modal Learning for Acquiring Concepts from Audio-visual Input
Katsuhiko Ishiguro (Univ. Tokyo), Nobuyuki Otsu (AIST/Univ. Tokyo), Yasuo Kuniyoshi (Univ. Tokyo) |
We propose an inter-modal learning system which acquires concepts
from auditory and visual information. The system ex... [more] |
PRMU2004-92
pp.17-24 |