Ekkasit Pinyoanuntapong (เอกสิทธิ์)

I am a Ph.D. student in the WiNS Lab at the University of North Carolina at Charlotte, advised by Prof. Pu Wang. My research interests lie in real-time, scene-aware 3D human motion generation, with a focus on controllability and high-quality synthesis. Currently, I am working on using text-to-motion to guide reinforcement learning through imitation learning, aiming to explore physically plausible motion in simulated environments. In my previous experience, I have worked on augmented reality, physics engine, motion detection and various animation software programs.

Selected Publications

ControlMM: Controllable Masked Motion Generation

Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, Sergey Tulyakov

Arxiv 2024.

Arxiv Webpage Github

BAMM: Bidirectional Autoregressive Motion Model

Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Pu Wang, Minwoo Lee, Srijan Das, Chen Chen

ECCV 2024.

Arxiv Webpage Github

MMM: Generative Masked Motion Model

Ekkasit Pinyoanuntapong, Pu Wang, Minwoo Lee, Chen Chen

CVPR 2024 (Highlight).

Arxiv Webpage Github

GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer

Ekkasit Pinyoanuntapong, Ayman Ali, Pu Wang, Minwoo Lee, Chen Chen

ICASSP 2023.

Arxiv Github

GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait Recognition

Ekkasit Pinyoanuntapong, Ayman Ali, Kalvik Jakkala, Pu Wang, Minwoo Lee, Qucheng Peng, Chen Chen, Zhi Sun

IEEE MASS 2023.

Arxiv Webpage Github

Skeleton-based Human Action Recognition via Convolutional Neural Networks

Ayman Ali, Ekkasit Pinyoanuntapong, Pu Wang, Mohsen Dorodchi

Arxiv 2023.

Arxiv