The 40th Annual Conference of the Japanese Society for Artificial Intelligence, 2026
Advanced Search

Session Details

General SessionGeneral session : GS-7 Vision, speech media processing

[2K4-GS-7b]Vision, speech media processing

Tue. Jun 9, 2026 1:30 PM - 3:00 PM JST
Tue. Jun 9, 2026 4:30 AM - 6:00 AM UTC
Room K(Middle room 201A)
1:30 PM - 1:45 PM JST(4:30 AM - 4:45 AM UTC)

[2K4-GS-7b-01]Mitigating Color Bias in Text-to-Image Diffusion Models via Orthogonal Latent Shift with Reconstructive Visual Embeddings

〇Koki Fujiya1, Zhihao Shao1, Yoshiaki Tanabe1, Kenta Watanabe1, Toshihiko Yamasaki1 (1. The University of Tokyo)
1:45 PM - 2:00 PM JST(4:45 AM - 5:00 AM UTC)

[2K4-GS-7b-02]Enhancing Third-Party Detectability Resistance for Diffusion-Based Video Watermarking

〇Taichi Ando1, Ryohei Orihara1, Yasuyuki Tahara1, Sei Yuichi1 (1. The University of Electro-Communications)
2:00 PM - 2:15 PM JST(5:00 AM - 5:15 AM UTC)

[2K4-GS-7b-03]Zero-Shot Classification Utilizing Visible Regions via Diffusion Inpainting Models

〇Ryota Suzuki1, Tatsuhito Hasegawa1 (1. University of Fukui)
2:15 PM - 2:30 PM JST(5:15 AM - 5:30 AM UTC)

[2K4-GS-7b-04]Guiding Cross-Attention with Geometric Correspondences for Virtual Try-On

〇Kosuke Takemoto1, Takafumi Koshinaka1 (1. Yokohama City University)
2:30 PM - 2:45 PM JST(5:30 AM - 5:45 AM UTC)

[2K4-GS-7b-05]An Image Style Transformation Method for Diverse “Kawaii” Expressions

〇Hiroto Doi1, Masanori Akiyoshi1 (1. Kanagawa University)
2:45 PM - 3:00 PM JST(5:45 AM - 6:00 AM UTC)

[2K4-GS-7b-06]Diversity-Aware Max@k Optimization for Improving Best-of-N Performance in Image Generation with Diffusion Models

〇Ku Onoda1, Yuta Oshima1, Shohei Taniguchi1, Soichiro Nishimori1, Paavo Parmas1, Hiroki Furuta, Yutaka Matsuo1 (1. The University of Tokyo)
Back to Category List