Thu, Mar 24 AM
09:30 - 11:30 |
| (1) |
09:30-10:00 |
Saliency Feature Representations for Image Captioning |
Kazuki Yoshii (TUT), Eric Nichols, Kotaro Funakoshi, Mikio Nakano (HRI-JP), Masaki Aono (TUT) |
| (2) |
10:00-10:30 |
Temporal Spotting of Human Actions in Video Based on Voting Framework with a Hierarchical Action Model |
Keita Hara, Kazuaki Nakamura, Noboru Babaguchi (Osaka Univ.) |
| (3) |
10:30-11:00 |
Geospatio-temporal knowledge discovery from tagged images |
Michitaka Fukushima, Naoko Nitta, Noboru Babaguchi (Osaka Univ.) |
| (4) |
11:00-11:30 |
Multi-User Localization Based on Trajectory Group Optimization Considering Characteristics of Individuals and Devices |
Kenji Imanishi (Osaka Univ.), Yoshimichi Ito (OECU), Noboru Babaguchi (Osaka Univ.) |
Thu, Mar 24 AM
10:00 - 11:30 |
| (5) |
10:00-10:30 |
View Point Shift of Fisheye Lens and Epipolar Geometry |
Nobuyuki Kita (AIST) |
| (6) |
10:30-11:00 |
Sensor Fusion Algorithm with Radar and Camera for Fast Target Recognition Using HOG and Machine Learning |
Yohei Oishi, Isamu Matsunami, Yasushi Yamazaki (Univ. of Kitakyu) |
| (7) |
11:00-11:30 |
Automatic Detection of Cross-Browser Presentation Incompatibilities based on the Comparisons of HTML Element Relationships and OCR Results |
Hiroshi Tanaka, Yusaku Fujii, Eigo Segawa (Fujitsu Labs.) |
| |
11:30-13:00 |
Lunch Break ( 90 min. ) |
Thu, Mar 24 PM
13:00 - 14:30 |
| (8) |
13:00-13:30 |
A smart device-based multifactor authentication system based on context awareness |
Ryo Okabe, Tomoaki Higashi, Yasushi Yamazaki (Kitakyushu Univ.), Tetsushi Ohki (AIST) |
| (9) |
13:30-14:00 |
3D Ear biometrics using SHOT |
Shun Isayama, Daichi Takayama, Daishi Watabe (SIT) |
| (10) |
14:00-14:30 |
A New Discriminant Function for Visible-Light Paper Artifact-Metrics |
Kuwakado Hidenori (Kansai Univ.) |
Thu, Mar 24 PM
13:00 - 14:30 |
| (11) |
13:00-13:30 |
Text-Line and Character Segmentation for Off-line Recognition of Handwritten Japanese Text |
Kha Cong Nguyen, Nakagawa Masaki (Tokyo Univ. of Agriculture and Tech.) |
| (12) |
13:30-14:00 |
Preparation of an Unconstrained Vietnamese Online Handwriting Database and Recognition Experiments by BLSTM |
Hung Tuan Nguyen, Cuong Tuan Nguyen (Tokyo Univ. of Agri. and Tech.), Pham The Bao (Ho Chi Minh City University of Science), Masaki Nakagawa (Tokyo Univ. of Agri. and Tech.) |
| (13) |
14:00-14:30 |
Reconsideration on Text/Non-text Classification for Online Handwritten Ink Documents by BLSTM Neural Networks |
Soichiro Inatani, Truyen Van Phan, Masaki Nakagawa (Tokyo Univ. of Agri. & Tech.) |
| |
14:30-14:45 |
Break ( 15 min. ) |
Thu, Mar 24 PM
14:45 - 18:05 |
| (14) |
14:45-15:45 |
[Invited Talk]
Multimodal human activity recognition using wearable and smartphone sensors |
Takuya Maekawa (Osaka Univ.) |
| |
15:45-15:55 |
Break ( 10 min. ) |
| (15) |
15:55-16:55 |
[Invited Talk]
Science and Engineering for Promoting Human Development
-- Expanding with Applied Behavior Analysis -- |
Junichi Yamamoto (Keio Univ.) |
| |
16:55-17:05 |
Break ( 10 min. ) |
| (16) |
17:05-18:05 |
[Invited Talk]
* |
Yasuyuki Sato (Matsuda & Partners) |
Fri, Mar 25 AM
09:45 - 10:45 |
| (17) |
09:45-10:15 |
Generation of gait feature with different view incorporating gait prior |
Daigo Muramatsu, Yasushi Makihara, Yasushi Yagi (Osaka Univ.) |
| (18) |
10:15-10:45 |
Cross-view Gait Recognition using Convolutional Neural Network |
Kohei Shiraga, Yasushi Makihara, Daigo Muramatsu (Osaka Univ.), Tomio Echigo (Osaka Electro-Communication Univ.), Yasushi Yagi (Osaka Univ.) |
Fri, Mar 25 AM
09:45 - 10:45 |
| (19) |
09:45-10:15 |
A preliminary study on interactive segmentation of pancreases from abdominal CT by use of Graph Cut with Homography transformed probabilistic atlases |
Takenobu Suzuki, Hotaka Takizawa, Hiroyuki Kudou, Toshiyuki Okada (Univ. Tsukuba) |
| (20) |
10:15-10:45 |
Vessel tracking from 3D CT images based on 2D cross-section analysis |
Akira Uchida, Toshiyuki Okada, Hotaka Takizawa, Hiroyuki Kudo, Yukio Oshiro, Nobuhiro Okochi (Univ. of Tsukuba) |
| |
10:45-11:00 |
Break ( 15 min. ) |
Fri, Mar 25 AM
11:00 - 11:30 |
| (21) |
11:00-11:30 |
Report of the 19th PRMU Algorithm Contests
-- Logo Quiz "What's the manufacture of the shoes?" -- |
Keiichiro Shirai (Shinshu Univ.), Ukyo Tanikawa (Nagoya Univ.), Seiya Iwata (Mie Univ.), Kensho Hara (Nagoya Univ.), Tsukasa Mori (Mie Univ.), Hirotaka Kato (Nagoya Univ.) |
| |
11:30-13:00 |
Lunch Break ( 90 min. ) |
Fri, Mar 25 PM
13:00 - 14:30 |
| (22) |
13:00-13:30 |
Boredom state estimation from spontaneous behaviors in multiparty conversations including a robot agent |
Yasuhiro Shibasaki (Tokyo Tech), Kotaro Funakoshi (HRI-JP), Koichi Shinoda (Tokyo Tech) |
| (23) |
13:30-14:00 |
Symbolisation of Scene Flow Field |
Tomoya Kato (Chiab Univ), Atushi Imiya (Chiba Univ) |
| (24) |
14:00-14:30 |
Worker Detection in Office Environment with Multi-weak Detectors for Human Shapes |
Yuichiro Fujimoto, Masano Nakayama, Hitomi Yokoyama, Ikuko Shimizu, Kinya Fujita (TUAT) |
Fri, Mar 25 PM
13:00 - 14:30 |
| (25) |
13:00-13:30 |
Camera-Based Method of Adding and Sharing Annotations for Diverse Documents |
Yusuke Oguma, Koichi Kise (Osaka Prefecture Univ.) |
| (26) |
13:30-14:00 |
Digital comic book reader using eye gaze information |
Mizuki Matsubara, Olivier Augereau, Motoi Iwata, Koichi Kise (OPU) |
| (27) |
14:00-14:30 |
Estimation of subjectively difficult words on documents by using gaze data |
Ayano Okoso, Shoya Ishimaru, Olivier Augereau, Koichi Kise (OPU) |
| |
14:30-14:45 |
Break ( 15 min. ) |
Fri, Mar 25 PM
14:45 - 16:45 |
| (28) |
14:45-15:15 |
Robust Action Detection Using Hough Forests under Scale Changes |
Kensho Hara, Kenji Mase (Nagoya Univ.) |
| (29) |
15:15-15:45 |
Scene and Actions: Combining Multiple Deep Features for Human Action Recognition |
Yasunori Kudo, Shunta Saito, Yoshimitsu Aoki (Keio Univ.) |
| (30) |
15:45-16:15 |
Orientation based Customer Pose Estimation from Surveillance Camera |
Jingewn Liu, Yanlei Gu, Shunsuke Kamijo (Univ. of Tokyo) |
| (31) |
16:15-16:45 |
A Levenberg-Marquardt-Based Face Tracking Method with Shape Estimation in Real-Time |
Kento Tsutsui, Tsuyoshi Migita, Takeshi Shakunaga (Okayama Univ.) |
Fri, Mar 25 PM
14:45 - 16:45 |
| (32) |
14:45-15:15 |
Omnidirectional Word Sensing System Guiding with Stereophonic Voice |
Taketsugu Miyata, Masakazu Iwamura, Koichi Kise (Osaka Prefecture Univ.) |
| (33) |
15:15-15:45 |
Experimental investigation for estimation method of English proficiency using eye gaze information |
Hiorki Fujiyoshi, Shoya Ishimaru, Olivier Augereau, Koichi Kise (Osaka Pre Univ) |
| (34) |
15:45-16:15 |
Efficient Mondrian Forests by Introducing Supervised Learning |
Ryuei Murata (Chubu Univ.), Akisato Kimura, Yoshitaka Ushiku (NTT), Takayoshi Yamashita, Yuji Yamauchi, Hironobu Fujiyoshi (Chubu Univ.) |
| (35) |
16:15-16:45 |
Tensor-Based Methods for Dimension Reduction of Volumetric Data |
Hayato Itoh, Atsushi Imiya (Chiba Univ.), Tomoya Sakai (Nagasaki Univ.) |
-or
zer
