Shugao Ma

14

Papers

9

Total Citations

Papers (14)

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization

Streaming VideoLLMs for Real-Time Procedural Video Understanding

Salient Object Subitizing

Space-Time Tree Ensemble for Action Recognition

Pixel Codec Avatars

Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and Synthesis

Data-Free Class-Incremental Hand Gesture Recognition

Expressive Telepresence via Modular Codec Avatars

LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space

Learning Activity Progression in LSTMs for Activity Detection and Early Detection

HuMoCon: Concept Discovery for Human Motion Understanding

POET: Prompt Offset Tuning for Continual Human Action Adaptation

Opening the Vocabulary of Egocentric Actions