Fri, Nov 29 AM 10:40 - 12:00 |
(1) |
10:40-10:55 |
|
(2) |
10:55-11:10 |
|
(3) |
11:10-11:25 |
|
(4) |
11:25-11:40 |
|
(5) |
11:40-12:00 |
|
Fri, Nov 29 AM 10:40 - 12:00 |
(6) PRMU |
10:40-10:55 |
Task Partitioning and Ordering for Continual Learning
-- Class Clustering from Confusion Matrix -- [updated] |
Toshikazu Wada (Wakayama Univ.) |
(7) PRMU |
10:55-11:10 |
The performance evaluation of DINO with the integration of the Attention modification mechanism using Sigmoid Attention. [updated] |
Yuki Matsumoto (SEI), Tomokazu Ozawa (Unico), Takuya Okuno (SCE), Katsushi Miura (SEI) |
(8) PRMU |
11:10-11:25 |
Learning Neural Velocity Fields using Edge-based Ray Sampling |
Sota Ito, Yoshikazu Hayashi (Gifu Univ.), Hiroaki Aizawa (Hiroshima Univ), Kunihito Kato (Gifu Univ.) |
(9) PRMU |
11:25-11:40 |
Self-supervised Contrastive Learning for Remote Sensing Imagery with Perlin noise injection |
Riku Okazawa, Eisaku Maeda (Tokyo Denki Univ.) |
(10) |
11:40-12:00 |
|
|
12:00-13:30 |
Lunch Break ( 90 min. ) |
Fri, Nov 29 PM 13:30 - 15:00 |
(11) PRMU |
13:30-15:00 |
[Tutorial Lecture]
The real world, 3D, robotics and language understanding
-- Beyond image and language understanding -- |
Shuhei Kurita (NII) |
|
15:00-15:10 |
Break ( 10 min. ) |
Fri, Nov 29 PM 15:10 - 16:30 |
(12) PRMU |
15:10-15:25 |
Theoretical Explanation for Learning from Adversarial Perturbations |
Soichiro Kumano (UTokyo), Hiroshi Kera (Chiba Univ.), Toshihiko Yamasaki (UTokyo) |
(13) PRMU |
15:25-15:40 |
|
|
(14) PRMU |
15:40-15:55 |
The Double Descent and The Acquisition of Concepts During The Learning Process. |
Shun Iwase, Reiya Hiramoto, Keito Kobayashi, Eisaku Maeda (TDU) [updated] |
(15) PRMU |
15:55-16:10 |
Robustness of DNN against Model Extraction Attacks |
Reiya Hiramoto, Shun Iwase, Eisaku Maeda (TDU) |
(16) |
16:10-16:30 |
|
|
16:30-16:40 |
Break ( 10 min. ) |
Fri, Nov 29 PM 15:10 - 16:30 |
(17) PRMU |
15:10-15:25 |
Determination of cardiac stenosis patients by CNN using 3D non-contrast cardiac CT data |
Tetsuya Asakawa (TUT), Masashi Hashimoto, Takeshi Miyaji, Kei Nomura, Kazuki Shimizu (THC), Masaki Aono (TUT) |
(18) |
15:25-15:40 |
|
(19) |
15:40-15:55 |
|
(20) |
15:55-16:10 |
|
(21) |
16:10-16:30 |
|
|
16:30-16:40 |
Break ( 10 min. ) |
Fri, Nov 29 PM 16:40 - 18:15 |
(22) |
16:40-16:55 |
|
(23) |
16:55-17:10 |
|
(24) |
17:10-17:25 |
|
(25) |
17:25-17:40 |
|
(26) |
17:40-17:55 |
|
(27) |
17:55-18:15 |
|
Fri, Nov 29 PM 16:40 - 17:45 [updated] |
(28) [updated] |
16:40-16:55 [updated] |
|
(29) [updated] |
16:55-17:10 [updated] |
|
(30) [updated] |
17:10-17:25 [updated] |
|
(31) [updated] |
17:25-17:45 [updated] |
|
Fri, Nov 29 PM 18:15 - 19:45 |
(32) [updated] |
18:15-19:45 |
|
Sat, Nov 30 AM 09:30 - 10:50 |
(33) PRMU [updated] |
09:30-09:45 |
Bezier Curve-Based Stroke Extraction for Handwritten Characters |
Yuxuan Teng, Takuya Matsuzaki (TUS) |
(34) PRMU [updated] |
09:45-10:00 |
Proposal of Weakly Supervised Disentanglement and Its Application to Text Image Analysis |
Hayato Mitani (Kyushu Univ.), Daichi Haraguchi, Wataru Shimoda, Naoto Inoue, Kota Yamaguchi (CyberAgent), Seiichi Uchida (Kyushu Univ.) |
(35) PRMU [updated] |
10:00-10:15 |
Composition of OCR Training Data towards Automated Marking of Transcription [updated] |
Ayumi Seki, Takuya Matsuzaki (TUS) [updated] |
(36) PRMU [updated] |
10:15-10:30 |
Completion of Mokkan Character Images by Diffusion Model |
Kenji Shiono, Wataru Ohyama (Tokyo Denki Univ.) |
(37) [updated] |
10:30-10:50 |
|
|
10:50-11:00 |
Break ( 10 min. ) |
Sat, Nov 30 AM 09:30 - 10:50 |
(38) PRMU [updated] |
09:30-09:45 |
Popularity Prediction on Fashion SNS with Multimodal Features |
Shun Okamoto, Satoshi Iizuka, Kazuhiro Fukui (Tsukuba Univ.) |
(39) PRMU [updated] |
09:45-10:00 |
A Study on Mental Health Estimation from Dietary Photo Logs Using Large Multimodal Models |
Yuki Imajuku, Yoko Yamakata, Kiyoharu Aizawa (UTokyo) |
(40) PRMU [updated] |
10:00-10:15 |
Matsue city rivers flood forecasting method based on gaussian process autoregression [updated] |
Kaisho Wakabayashi, Hitoshi Sakano, Hiroshi Yajima (Shimane University) |
(41) PRMU [updated] |
10:15-10:30 |
Disentangle Learning for Interactive Semiconductor Inspection Robust to Thin-Film Interference |
Koki Mitsusada, Koji Kamma, Toshikazu Wada (Wakayama Univ.), Yasuhiro Hamada, Yoshinori Shimada, Takeshi Noguchi, Toshiyuki Okayama (Advanced System Solutions Co., Ltd.) |
(42) [updated] |
10:30-10:50 |
|
|
10:50-11:00 |
Break ( 10 min. ) |
Sat, Nov 30 AM 11:00 - 12:00 |
(43) PRMU [updated] |
11:00-12:00 |
[Invited Talk]
Deep image synthesis with physical and geometrical constraints |
Takuhiro Kaneko (NTT) |
|
12:00-13:30 |
Lunch Break ( 90 min. ) |
Sat, Nov 30 PM 13:30 - 14:30 |
(44) PRMU [updated] |
13:30-14:30 |
[Invited Talk]
Graphic design generation by multi-modal models [updated] |
Naoto Inoue (CA) |
|
14:30-14:40 |
Break ( 10 min. ) |
Sat, Nov 30 PM 14:40 - 16:00 |
(45) PRMU [updated] |
14:40-14:55 |
Analysis of Latent Features from Adversarial Examples on Perception and Reconstruction [updated] |
Takumi Maeda (Koshi High School), Soichiro Kumano, Toshihiko Yamasaki (UTokyo) |
(46) PRMU [updated] |
14:55-15:10 |
|
|
(47) PRMU [updated] |
15:10-15:25 |
A New Weighting Strategy for Group Robust Classification |
Yuya Saito, Shinnosuke Matsuo, Seiichi Uchida (Kyushu Univ.), Daiki Suehiro (Kyushu Univ./RIKEN AIP) |
(48) PRMU [updated] |
15:25-15:40 |
Subspace-Based Decision Tree Retraining |
Yoriaki Murata, Hitoshi Sakano (Shimane Univ) |
(49) [updated] |
15:40-16:00 |
|
|
16:00-16:10 |
Break ( 10 min. ) |
Sat, Nov 30 PM 14:40 - 15:45 [updated] |
(50) PRMU [updated] |
14:40-14:55 |
CommonArt
-- Diffusion Transformer for Image Generation by Japanese Large Language Model -- |
Yasunori Ozaki, Ryuji Mishima, Toshiki Tomihira |
(51) [updated] |
14:55-15:10 [updated] |
|
(52) [updated] |
15:10-15:25 [updated] |
|
(53) [updated] |
15:25-15:45 [updated] |
|
|
15:45-16:10 [updated] |
Break ( 25 min. ) [updated] |
Sat, Nov 30 PM 16:10 - 16:20 |
(54) [updated] |
16:10-16:20 |
|