Thu, Feb 21 AM
09:30 - 11:30 |
| (1) |
09:30-10:00 |
A Mobile Camera Localization Method by Referring Correspondence Points with an Aerial Image  PRMU2012-130 |
Hisatoshi Toriya, Itaru Kitahara, Yuichi Ohta (Univ. of Tsukuba) |
| (2) |
10:00-10:30 |
Cylinder-shaped object detection from three-dimensional point cloud using the local point shape and cylinder model PRMU2012-131 |
Hitoshi Niigaki, Jun Shimamura, Hiroyuki Arai, Yukinobu Taniguchi (NTT) |
| (3) |
10:30-11:00 |
Topic extraction about 3D constitution for occlusion boundary detection PRMU2012-132 |
Kazuhiko Murasaki, Kyoko Sudo, Yukinobu Taniguchi (NTT) |
| (4) |
11:00-11:30 |
INDIVIDUAL PREFERENCE ANALYSIS WITH SOCIALITY-AWARE TOPIC MODEL FOR PERSONALIZED IMAGE RETRIVAL PRMU2012-133 |
Kaori Kataoka, Akisato Kimura, Kazuhiko Murasaki, Kyoko Sudo, Yukinobu Taniguchi (NTT) |
Thu, Feb 21 AM
09:30 - 11:30 |
| (5) |
09:30-10:00 |
Reconstruction-based super resolution by anisotropic diffusion constraint and total variation regularization PRMU2012-134 |
Takashi Shibata, Akihiko Iketani, Shuji Senda (NEC) |
| (6) |
10:00-10:30 |
Human Character Generation from Prerecorded Videos for Mixed Reality PRMU2012-135 |
Tomoya Takeda, Takeshi Oishi (Univ. of Tokyo), Atsuhiko Banno (AIST), Katsushi Ikeuchi (Univ. of Tokyo) |
| (7) |
10:30-11:00 |
Shape Alignment for 3D Model Searching PRMU2012-136 |
Seigo Matsumoto, Kazuhiro Fukui (Univ. of Tsukuba) |
| (8) |
11:00-11:30 |
RGB-D Based 3D-Object Recognition by LLC Using Depth Spatial Pyramid PRMU2012-137 |
Takahiro Hori, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| |
11:30-13:00 |
Break ( 90 min. ) |
Thu, Feb 21 PM
13:00 - 13:50 |
| (9) |
13:00-13:50 |
[Special Talk]
Analysis and applications of a large-scale news video archive PRMU2012-138 |
Ichiro Ide (Nagoya Univ.) |
| |
13:50-14:00 |
Break ( 10 min. ) |
Thu, Feb 21 PM
14:00 - 16:00 |
| (10) |
14:00-14:30 |
High-dimensional non-parametric probability density estimation using self organizing incremental neural network PRMU2012-139 |
Hiroshi Takahashi, Yoshihiro Nakamura, Osamu Hasegawa (Titech) |
| (11) |
14:30-15:00 |
Memory Efficient K-means Clustering Using HDD PRMU2012-140 |
Hiroshi Oike, Kazuyoshi Kishi, Toshikazu Wada (Wakayama Univ.) |
| (12) |
15:00-15:30 |
Fast online multivariate non-parametric density estimation under noisy environment PRMU2012-141 |
Yoshihiro Nakamura, Hiroshi Takahashi, Osamu Hasegawa (Titech) |
| (13) |
15:30-16:00 |
Fast and Memory Efficient Approximate Nearest Neighbor Search with Distance Estimation Based on Space Indexing PRMU2012-142 |
Tomokazu Sato, Masakazu Iwamura, Koichi Kise (Osaka Pref Univ.) |
Thu, Feb 21 PM
14:00 - 16:00 |
| (14) |
14:00-14:30 |
A grasping-support method based on computed visual-auditory feedback for visually impaired persons
-- .* -- PRMU2012-143 |
Fei Cheng, Michael Hild (Osaka Electro-Comm. Univ.) |
| (15) |
14:30-15:00 |
Object Recognition by the Kinect Cane System and its Performance Evaluation PRMU2012-144 |
Shotaro Yamaguchi, Hotaka Takizawa, Mayumi Aoyagi (Univ of Tsukuba), Nobuo Ezaki (Toba National College of Maritime Technology), Shinji Mizuno (Aichi Institute of Technology) |
| (16) |
15:00-15:30 |
Saliency-Based Image Modulation for Gaze Navigation PRMU2012-145 |
Aiko Hagiwara (Chiba Univ.), Akihiro Sugimoto (NII), Kazuhiko Kawamoto (Chiba Univ.) |
| (17) |
15:30-16:00 |
Recognition of "Want to Speak''/"Want to Hear'' Communicative Expressions from Facial Features PRMU2012-146 |
Yuichi Watanabe, Daisuke Fukatsu, Naoki Mukawa (Tokyo Denki Univ.) |
| |
16:00-16:10 |
Break ( 10 min. ) |
Thu, Feb 21 PM
16:10 - 17:40 |
| (18) |
16:10-16:40 |
[Poster Presentation]
Evaluation and Expansion of Recognition methods Using Unlabeled Regions by means of Self-training PRMU2012-147 |
Daichi Tanabe, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Yoko Kominami, Rie Miyaki, Taiji Matsuo, Shigeto Yoshida, Shinji Tanaka (Hiroshima Univ.) |
| (19) |
16:10-16:40 |
[Poster Presentation]
Towards Realtime Computation of Dense Optical Flow using Time-Correlation Image Sensor PRMU2012-148 |
Go Oishi, Tomohiro Kitagawa, Hidekata Hontani (Nagoya Inst. of Tech.) |
| (20) |
16:10-16:40 |
[Poster Presentation]
An ICA approach to analysis of SK model
-- case of one-step RSB -- PRMU2012-149 |
Takaaki Sato, Masato Inoue (Waseda Univ.) |
| (21) |
16:10-16:40 |
[Poster Presentation]
Triangle-based Partial Geometric Retrieval PRMU2012-150 |
Hiromasa Takei, Hayato Yamana (Waseda Univ.) |
| (22) |
16:10-16:40 |
[Poster Presentation]
Estimation of Camera Yaw angle by Regression Forests using Multiple Paths PRMU2012-151 |
Ryoji Wakayama, Hironobu Fujiyoshi (Chubu Univ.) |
| (23) |
16:10-16:40 |
[Poster Presentation]
Detection of facial features by circular Hough transform and histogram of gradient PRMU2012-152 |
Yuya Yoshizawa, Wataru Ohyama, Tetsushi Wakabayashi, Fumitaka Kimura (Mie Univ) |
| (24) |
16:10-16:40 |
[Poster Presentation]
A Study on Video Semantic Indexing by Subspace Method PRMU2012-153 |
Fukushi Tanaka, Seiji Hotta (Tokyo Univ. of Agriculture and Tech.) |
| (25) |
16:10-16:40 |
[Poster Presentation]
A GPGPU Approach for Accelerating Eyes Extraction from Frontal Face Images PRMU2012-154 |
Hayato Iwasa, Wataru Ohyama, Tetsushi Wakabayashi, Fumitaka Kimura (Mie Univ.) |
| (26) |
16:10-16:40 |
[Poster Presentation]
Appearance-Based Character Recognition in Natural Images Using Subspace Classifier PRMU2012-155 |
Keisuke Higa, Seiji Hotta (Tokyo Univ. of Agriculture and Tech.) |
| (27) |
16:10-16:40 |
[Poster Presentation]
Study of pointing gesture recognition for pointing and calling using compressed sensing PRMU2012-156 |
Masahiro Iwasaki, Kaori Fujinami (Tokyo Univ. of Agriculture and Tech.) |
| (28) |
16:10-16:40 |
[Poster Presentation]
Image compression method for transmitting high-definition character information PRMU2012-157 |
Shota Kaneko, Yoshihiro Sugaya, Shinichiro Omachi (Tohoku Univ.) |
| (29) |
16:10-16:40 |
[Poster Presentation]
Information embedment into the character pattern with color for recognition PRMU2012-158 |
Shohei Okugi, Yoshihiro Sugaya, Shinichiro Omachi (Tohoku Univ.) |
| (30) |
16:10-16:40 |
[Poster Presentation]
Traffic lights recognition considering color saturation with Stereo Cameras on the Vehicle PRMU2012-159 |
Hiroki Moizumi, Yoshihiro Sugaya (Tohoku Univ.), Masako Omachi (Sendai NCT), Shinichiro Omachi (Tohoku Univ.) |
| (31) |
16:10-16:40 |
[Poster Presentation]
Study on the Optimization of Behavior Recognition Method Using the Location Information of the Smart Phone PRMU2012-160 |
Kazuya Ohta, Masahiro Iwasaki, Kaori Fujinami (Tokyo Univ. of Agriculture and Tech.) |
| (32) |
16:10-17:40 |
|
Fri, Feb 22 AM
09:30 - 10:30 |
| (33) |
09:30-10:00 |
* PRMU2012-161 |
Kazutaka Takeda, Koichi Kise, Masakazu Iwamura (Osaka Prefecture. Univ) |
| (34) |
10:00-10:30 |
Grafting Trees A Nearest Neighbor Srarch Algorithm without Distance Computation PRMU2012-162 |
Yohei Ohtani, Toshikazu Wada, Hiroshi Oike (Wakayama Univ.) |
Fri, Feb 22 AM
09:00 - 10:30 |
| (35) |
09:00-09:30 |
Variational Computation of Mean Shape PRMU2012-163 |
Shun Inagaki, Atsushi Imiya (Chiba Univ.), Hidekata Hontani (Nagoya Inst. of Tech.), Shouhei Hanaoka, Yoshitaka Masutani (Univ. of Tokyo) |
| (36) |
09:30-10:00 |
Extended separable lattice HMMs based on state duration control for recognition of images with variations PRMU2012-164 |
Takaya Makino, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
| (37) |
10:00-10:30 |
Image recognition based on hidden Markov eigen-image models with the variational Bayesian method PRMU2012-165 |
Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
| |
10:30-10:40 |
Break ( 10 min. ) |
Fri, Feb 22 AM
10:40 - 11:30 |
| (38) |
10:40-11:30 |
[Special Talk]
Social curation as corpora for large-scale multimedia content analysis PRMU2012-166 |
Akisato Kimura (NTT) |
| |
11:30-13:00 |
Break ( 90 min. ) |
Fri, Feb 22 PM
13:00 - 13:50 |
| (39) |
13:00-13:50 |
[Special Talk]
Smart Posterboard: Multi-modal Sensing and Recognition of Poster Presentation PRMU2012-167 |
Tatsuya Kawahara (Kyoto Univ.) |
| |
13:50-14:00 |
Break ( 10 min. ) |
Fri, Feb 22 PM
14:00 - 15:30 |
| (40) |
14:00-14:30 |
Video Semantic Indexing Using Video-Clip Scores and GMM Supervectors PRMU2012-168 |
Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) |
| (41) |
14:30-15:00 |
Semantic Video Concept Detection using Subspace-partition based Scheme
-- TRECVid 2012 Semantic Video Concept Detection by NTT -- PRMU2012-169 |
Yongqing Sun, Kyoko Sudo, Yukinobu Taniguchi (NTT), Haojie Li, Lei Yi, Yue Guan (Dalian Univ. of Tech.) |
| (42) |
15:00-15:30 |
Multimedia event detection using camera motion cancelled features and GMM supervectors PRMU2012-170 |
Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) |
Fri, Feb 22 PM
14:00 - 15:30 |
| (43) |
14:00-14:30 |
A learning clustering method for taste data based on user food preference PRMU2012-171 |
Daigo Takano (Future Univ. Hakodate) |
| (44) |
14:30-15:00 |
Sequence Number-free Detection of Similar Sequences Among Multiple Sequences
-- Proposal of Circle Continuous Dynamic Programming -- PRMU2012-172 |
Ryuichi Oka (Aizu Univ.) |
| (45) |
15:00-15:30 |
Basis Function Construction for Nonlinear Time Series Prediction PRMU2012-173 |
Shota Tsukada, Hideki Satoh (Future Univ Hakodate) |
| |
15:30-15:40 |
Break ( 10 min. ) |
Fri, Feb 22 PM
15:40 - 17:10 |
| (46) |
15:40-16:10 |
* PRMU2012-174 |
Tomohiro Sakata, Nobuaki Matozaki, Koichi Kise, Masakazu Iwamura (Osaka Prefecture Univ.) |
| (47) |
16:10-16:40 |
Instance Video Search by Images as a Query PRMU2012-175 |
Masaya Murata, Hidehisa Nagano, Ryo Mukai, Kunio Kashino (NTT), Shin'ichi Satoh (NII) |
| (48) |
16:40-17:10 |
Large-scale Web Video Shot Ranking Exploiting Visual Features and Tag Co-occurrence PRMU2012-176 |
Do Hang Nga, Keiji Yanai (Univ. of Electro- Comm.) |
Fri, Feb 22 PM
15:40 - 17:10 |
| (49) |
15:40-16:10 |
GPU based implementation of the Human Detection and Tracking by Using Fish-eye Camera PRMU2012-177 |
Katsuhisa Kitaguchi, Mamoru Saito (OMTRI) |
| (50) |
16:10-16:40 |
Gait-based biometric identification from invisible shadows PRMU2012-178 |
Koji Uchino, Yumi Iwashita, Ryo Kurazume (Kyushu Univ.), Adrian Stoica (JPL) |
| (51) |
16:40-17:10 |
An Embedded Background Modeling Method for Detecting Object Left Behind and Very Still Person PRMU2012-179 |
Thi Thi Zin, Hiromitsu Hama, Takashi Toriu, Pyke Tin (Osaka City Univ.) |
-
n
