Thu, Mar 13 AM
09:00 - 10:30 |
| (1) |
09:00-09:30 |
Image Preference Estimation with Gaze and Image Features |
Yasunori Ozaki, Yusuke Sugano, Yoichi Sato (Univ. of Tokyo) |
| (2) |
09:30-10:00 |
Matching by Quadratic Programming for Manga Colorization |
Kazuhiro Sato, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa (Univ. of Tokyo) |
| (3) |
10:00-10:30 |
Velocity Pyramid for Event Detection |
Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) |
Thu, Mar 13 AM
09:00 - 10:30 |
| (4) |
09:00-09:30 |
Development of Baggage Trajectory Retrieval System using Surveillance Camera |
Kenichi Yoneji, Yuki Watanabe, Daisuke Matsubara, Atsushi Hiroike, Nobuo Nukaga (Hitachi) |
| (5) |
09:30-10:00 |
Person Retrieval System for Surveillance Video Analysis using Multi-Perspective Features |
Yuki Watanabe, Daisuke Matsubara, Kenichi Yoneji, Tomoaki Yoshinaga, Nobuo Nukaga, Atsushi Hiroike (Hitachi) |
| (6) |
10:00-10:30 |
Discovery of Spatio-Temporal Patterns from Foursquare by Diffusion-type Estimation and ICA |
Yoshitatsu Matsuda, Kazunori Yamaguchi, Ken-ichiro Nishioka (Univ. of Tokyo) |
| |
10:30-10:45 |
Break ( 15 min. ) |
Thu, Mar 13 AM
10:45 - 12:15 |
| (7) |
10:45-11:15 |
A proposal of Foreign language conversation learning based on Direct Method by a Robot Teacher |
Yusuke Ikemoto, Hirokazu Matsui, Saki Uchida (Mie Univ.) |
| (8) |
11:15-11:45 |
Violent Scenes Detection in Videos using Automatically Inferred Mid-level Concepts |
Shinichi Goto, Terumasa Aoki (Tohoku Univ.) |
| (9) |
11:45-12:15 |
Large-Scale Japanese Scene Text Dataset OPU-JST-1 |
Hitomi Sato, Takahiro Matsuda, Yuki Ikeda, Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ.) |
Thu, Mar 13 AM
10:45 - 12:15 |
| (10) |
10:45-11:15 |
Fault Detection in Cardio-Pulmonary Bypass Based on Multiple Time Series Patterns |
Ryota Imafuku, Masayuki Tanaka, Kyota Izumi, Shun Nagase, Tohgoroh Matsui, Yasushi Kodama (Chubu Univ.) |
| (11) |
11:15-11:45 |
Shape measurement of biological tissue by using 3D endoscope based on active stereo method |
Ryo Furukawa, Ishin Nishitani, Masahito Aoyama, Shinsaku Hiura (Hiroshima City Univ.), Hirooki Aoki (Chitose Inst. Sci. Tech.), Yoko Kominami, Taiji Matsuo, Shigeto Yoshida, Shinji Tanaka (Hiroshima Univ.), Ryusuke Sagawa (AIST), Hiroshi Kawasaki (Kagoshima Univ.) |
| (12) |
11:45-12:15 |
Bioimage-informatics |
Ayumi Hamano (Kyushu Univ.), Natsumaro Kutsuna (Univ. of Tokyo), Toshihiko Fujimori (NIBB), Kazuhiro Tateishi, Sachiko Tsukita (Osaka Univ.), Seiichi Uchida (Kyushu Univ.) |
| |
12:15-13:15 |
Lunch Break ( 60 min. ) |
Thu, Mar 13 PM
13:15 - 14:15 |
| (13) |
13:15-14:15 |
[Special Talk]
Trial Realization of Associative Search for Media Understanding |
Miki Haseyama (Hokkaido Univ.) |
| |
14:15-14:30 |
Break ( 15 min. ) |
Thu, Mar 13 PM
14:30 - 16:30 |
| (14) |
14:30-15:00 |
* |
Hitoshi Kawaichi, Kai Kunze, Koichi Kise (Osaka Prefecture Univ.) |
| (15) |
15:00-15:30 |
* |
Wakana Suzuki (Osaka Prefecture Univ), Takumi Toyama (DFKI), Kai Kunze, Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ), Andreas Dengel (DFKI), Andreas Bulling |
| (16) |
15:30-16:00 |
* |
Nobuaki Matozaki, Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ.) |
| (17) |
16:00-16:30 |
Neighbor-to-Neighbor Search for Fast Image Classification |
Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) |
| |
16:30-16:45 |
Break ( 15 min. ) |
Thu, Mar 13 PM
14:30 - 16:00 |
| (18) |
14:30-15:00 |
Restoration of Archaeological Artifacts Based on ORB Image Features |
Koji Kashihara (Univ. of Tokushima) |
| (19) |
15:00-15:30 |
Proposal of the weighted voting type co-training method for the construction of an accurate traffic sign detector |
Yuji Kojima, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase (Nagoya Univ.) |
| (20) |
15:30-16:00 |
Accuracy improvement of pedestrian detection from in-vehicle camera images based on environment adaptation using location information |
Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase (Nagoya Univ.), Hiroyuki Ishida, Yoshiko Kojima (Toyota Central R&D Labs) |
| |
16:00-16:15 |
Break ( 15 min. ) |
Thu, Mar 13 PM
16:45 - 17:45 |
| (21) |
16:45-17:15 |
A 3D Model Matching Method with Projection and its Evaluation |
Yuki Hida, Yoshiaki Usui, O Tenu, Takumi Sato, Kaoru Katayama (Tokyo Metropolitan Univ.) |
| (22) |
17:15-17:45 |
Study of Clustering Feature points of Moving Objects From Dynamic RGB-D Images
-- Proposing a Method that Combines Supervoxel and Multi Label Graph-Cut -- |
Naotomo Tatematsu, Jun Ohya (Waseda Univ.), Larry S. Davis (Univ. of Maryland) |
Thu, Mar 13 PM
16:15 - 17:15 |
| (23) |
16:15-16:45 |
Study of Tongue Detection and Tongue Shape Classification Based on Active Contour Model and Texture Features |
Ming Tian, Luo Dan, Jun Ohya (Waseda Univ.) |
| (24) |
16:45-17:15 |
Construction of a Bayesian network model for the prediction of medical costs of lifestyle-related diseases using checkup data and claims data |
Toshinori Miyoshi, Yasutaka Hasegawa, Hideyuki Ban (Hitachi), Shoji Negishi, Norihito Kunichika, Takuzo Muneshige (Hitachi-kenpo) |
Fri, Mar 14 AM
09:00 - 10:30 |
| (25) |
09:00-09:30 |
Hierarchical Single Image Super-Resolution Based on Dictionary Learning |
Toshihiro Kitao, Osamu Hasegawa (Tokyo Inst. of Tech.) |
| (26) |
09:30-10:00 |
Study of Recognizing Hand Actions from Video Sequences during Suture Surgeries Based on Temporally-Sectioned SIFT and Sliding Window Based Neural Networks |
Ye Li, Jun Ohya (Waseda Univ.), Toshio Chiba (NCCHD), Rong Xu (Waseda Univ.), Hiromasa Yamashita (NCCHD) |
| (27) |
10:00-10:30 |
Fundamental Study of Recognizing Customers' Behaviors in Shops Based on Facial Expression Analysis
-- Acquiring Facial Expression Features by ASM and How to Build Bayesian Networks' Models -- |
Luwei Jia, Jun Ohya, Takayuki Hori (Waseda Univ.) |
Fri, Mar 14 AM
09:00 - 10:30 |
| (28) |
09:00-09:30 |
SNAPPER:Fashion Coordinate Image Retrieval System |
Shinya Miura, Toshihiko Yamasaki, Kiyoharu Aizawa (Univ. of Tokyo) |
| (29) |
09:30-10:00 |
Dynamic Attribute Discovery via Incremental Category Learning |
Takayuki Umeda, Yongqing Sun, Go Irie, Kyoko Sudo, Yukinobu Taniguchi (NTT) |
| (30) |
10:00-10:30 |
Object recognition featuring decision-value based true/false classification and two-stage learning |
Toshihiko Yamasaki, Takaki Maeda, Kiyoharu Aizawa (Univ. of Tokyo) |
| |
10:30-10:45 |
Break ( 15 min. ) |
Fri, Mar 14 AM
10:45 - 12:15 |
| (31) |
10:45-11:15 |
A study on multi-modal speech recognition using depth images |
Naoya Ukai, Satoshi Tamura, Satoru Hayamizu (Gifu Univ.) |
| (32) |
11:15-11:45 |
Application of multi-modal speech interface in real environments |
Takumi Seko, Takuya Kawasaki, Satoshi Tamura, Satoru Hayamizu (Gifu Univ.) |
| (33) |
11:45-12:15 |
Image Retrieval Based on Group Photo Database Organization |
Yujiro Nakai, Naoko Nitta, Noboru Babaguchi (Osaka Univ.) |
Fri, Mar 14 AM
10:45 - 12:15 |
| (34) |
10:45-11:15 |
Evaluation of image local features for the improvement of face tracking accuracy |
Shogo Kawai, Maiya Hori, Hiroki Yoshimura, Yoshio Iwai (Tottori Univ.) |
| (35) |
11:15-11:45 |
Facial motion recognition Based on Dense and Detailed Motion data |
Yasuhiro Akagi, Yuka Kobaru, Hiroki Morinaga, Hiroshi Kawasaki (Kagoshima Univ.) |
| (36) |
11:45-12:15 |
* |
Yuya Kato, Yuzuko Utsumi, Kai Kunze, Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ.) |
| |
12:15-13:15 |
Lunch Break ( 60 min. ) |
Fri, Mar 14 PM
13:15 - 14:15 |
| (37) |
13:15-14:15 |
[Special Talk]
Image Utilization in the Information Service for Cultural Properties |
Yuzo Marukawa (National Museum of Ethnology) |
| |
14:15-14:30 |
Break ( 15 min. ) |
Fri, Mar 14 PM
14:30 - 16:00 |
| (38) |
14:30-15:00 |
Visually Natural Privacy Protection for Maintaining Image Context |
Tatsuya Koyama (Osaka Univ.), Yuta Nakashima (NAIST), Noboru Babaguchi (Osaka Univ.) |
| (39) |
15:00-15:30 |
Estimating Techinical Elements of Figure Skate Event from TV Braoadcast |
Satoru Morita, Yuto Honda (Yamaguchi Univ.) |
| (40) |
15:30-16:00 |
Repot of the 17th PRMU Algorithm Contest
-- Found them! Who's hiding? Where? -- |
Wataru Ohyama (Mie Univ.), Kensho Hara (Nagoya Univ.), Yuichi Kanematsu (Chukyo Univ.), Tetsuya Ito (Hiroshima City Univ.), Kazuya Gondou (Miyazaki Univ.), Tsubasa Minematsu (Kyushu Univ.), Naoki Kobayashi (Univ. of Tsukuba), Yoshimasa Sato (Chukyo Univ.) |
Fri, Mar 14 PM
14:30 - 16:00 |
| (41) |
14:30-15:00 |
Reflectance Separation under Varying Light Source Colors and Directions |
Akiko Ikeda, Takahiro Okabe (Kyushu Inst. of Tech.) |
| (42) |
15:00-15:30 |
Feature Extraction Using Local Gradient Pattern |
Hiroki Terashima, Takuya Kida (Hokkaido Univ.) |
| (43) |
15:30-16:00 |
Experimental study on effect of pre-training in deep learning through visualization of unit outputs |
Tsubasa Ochiai (Doshisha Univ./NICT), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT) |
| |
16:00-16:15 |
Break ( 15 min. ) |
Fri, Mar 14 PM
16:15 - 17:15 |
| (44) |
16:15-16:45 |
Car tracking for rear confirmation support by particle filter considering particular motions of a bicycle in angular change and vertical vibration |
Youhei Mikami (Waseda Univ.), Norikazu Ikoma (Kyushu Inst. of Tech.), Takeshi Ikenaga (Waseda Univ.) |
| (45) |
16:45-17:15 |
Hand contour compensation based-on motion feature with tracking and click action detection based-on dual threshold of finger length for HCI with vehicle systems |
Yuichiro Kitao, Takeshi Ikenaga (Waseda Univ.) |
Fri, Mar 14 PM
16:15 - 17:15 |
| (46) |
16:15-16:45 |
Transformation from a Parametric Curve to Lines |
Ken Miyamoto, Masahiro Abukawa (Mitsubishi Electric) |
| (47) |
16:45-17:15 |
Extraction of Curves from a Grayscale Image |
Yuki Inoue, Yasumasa Kanada (Univ. of Tokyo) |
-
n
