[3A1-GS-5] Agents:

[3A1-GS-5-03] Effects of Style Transformation of CG Avatar Gestures on User Impressions

〇Yoshiki Takahashi¹, Jie Zeng², Tatsuya Sakato², Yukiko Nakano² (1. Seikei University Graduate School of Science and Technology, 2. Seikei University Faculty of Science and Technology)

Keywords:Avatar, Gesture styles, User impressions

When people form impressions of others in face-to-face communication, gesture style (i.e. the way of gesturing) impacts their impressions, such as well-mannered, honest, and enthusiastic. In this study, we trained a deep-learning model for gesture style transfer using YouTube videos, and developed a system that generates CG avatar animations from motion data to which the style transfer was applied. We also proposed a method to select an appropriate style by fine-tuning a Large Language Model (LLM). Finally, a user study was conducted to verify whether the impression of the motion generated by applying the selected style was close to what the user intended.