Fri, Nov 21 PM
13:00 - 16:40 |
| (1) |
13:00-13:30 |
[Invited Talk]
Recent research trends in processors for deep learning and large language models (LLMs) |
Kentaro Yoshioka (Keio) |
| (2) |
13:30-14:00 |
[Invited Talk]
A Novel 1/1.3-inch 50 Megapixel three-wafer-stacked CMOS Image Sensor with DNN Circuit for Edge Processing |
Ryoichi Nakamura, Hidenobu Tsugawa, Wataru Otsuka, Kan Shimizu, Yoshihisa Kagawa, Kenta Ono, Yosuke Horie (Sony Semiconductor Solutions) |
| (3) |
14:00-14:30 |
[Invited Talk]
Combining Coded-Aperture, Event Camera, and Deep Learning for Light Field Imaging |
Keita Takahashi (Nagoya Univ.) |
| |
14:30-14:50 |
Break ( 20 min. ) |
| (4) |
14:50-15:20 |
[Invited Talk]
High-speed Vision X Deep Learning and its Application to Intelligent Systems |
Yuji Yamakawa (The Univ. of Tokyo) |
| (5) |
15:20-15:50 |
[Invited Talk]
What can event cameras be applied to? Scene and human state estimation using event based cameras |
Mariko Isogawa (Keio) |
| (6) |
15:50-16:20 |
[Invited Talk]
Blur restration and 3D reconstruction from microscopic images |
Hajime Nagahara (U Osaka) |
| (7) |
16:20-16:40 |
Faithful signal reconstruction using deep learning for flash LiDAR using charge-domain time-compressive ToF image sensor |
Daisuke Hayashi (Shizuoka Univ.), Michitaka Yoshida (Okayama Univ.), Keiichiro Kagawa (Shizuoka Univ.), Hajime Nagahara (UOsaka) |