Jyun-Ting Song — accepted AI-conference papers

2026

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Yichen Peng, Jyun-Ting Song, Siyeol Jung, Ulsan National Institute of Science & Technology blank, Ruofan Liu, Haiyang Liu +5

CVPR 2026

Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between

Cited by 0 Source ↗Scholar ↗

2026

Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors

Ryosuke Hori, Jyun-Ting Song, Zhengyi Luo, Jinkun Cao, Soyong Shin, Hideo Saito +1

CVPR 2026

We propose Ground Reaction Inertial Poser (GRIP), a method that reconstructs physically plausible human motion using four wearable devices. Unlike conventional IMU-only approaches, GRIP combines IMU signals with foot pressure data to capture both body dynamics and ground interactions. Furthermore, r

Cited by 0 Source ↗Scholar ↗

2024

Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions

Rawal Khirodkar, Jyun-Ting Song, Jinkun Cao, Zhengyi Luo, Kris M. Kitani

NeurIPS 2024poster

Understanding how humans interact with each other is key to building realistic multi-human virtual reality systems. This area remains relatively unexplored due to the lack of large-scale datasets. Recent datasets focusing on this issue mainly consist of activities captured entirely in controlled ind…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗