[3N6-GS-7] Vision, speech media processing:

Thu. May 29, 2025 5:40 PM - 7:20 PM Room N (Room 1009)

座長：壹岐太一（NTT）

+Add all to schedule

5:40 PM - 6:00 PM

[3N6-GS-7-01] Towards Evaluating the Performance of Vision-Language Models

〇Shunki Uebayashi¹, Kento Masui², Kyohei Atarashi¹, Han Bao¹, Hisashi Kashima¹, Mayu Otani², Koh Takeuchi¹ (1. Kyoto University, 2. CyberAgent)

6:00 PM - 6:20 PM

[3N6-GS-7-02] A Preliminary Study on Behavioral Analysis Using Vision and Language Foundation Model for Automobile Assembly Work Videos

〇Koki Kiyota¹, Kanta Kubo¹, Asuka Hisatomi², Hirotaka Ito², Yuta Higashizono², Satoshi Ono¹ (1. Kagoshima University, 2. TOYOTA AUTO BODY Research & Development)

[[Online]]

6:20 PM - 6:40 PM

[3N6-GS-7-03] Exploring VLM Image Token Contributions for Visual Recognition Learning

〇Koichiro Ito¹, Yasuuki Kaneko¹, Shintaro Hashimoto¹, Naoki Ishihama¹ (1. JAXA)

6:40 PM - 7:00 PM

[3N6-GS-7-04] Unlocking the Potential of Vision-Language Models

Enhancing Spatial Cognition through Multi-Layer Cognitive Maps and Spatial Information Prompts

〇Qi Feng¹ (1. Kyoto University)

7:00 PM - 7:20 PM

[3N6-GS-7-05] Machine Translation of Cooking Videos Using Chain-of-Thought with Image Descriptions

〇Kazuyoshi Takata¹, Takashi Ninomiya¹, Isao Goto¹ (1. Ehime University )

Session information