Picture for Wenzheng Zeng

Wenzheng Zeng

DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios

Add code
Oct 13, 2024
Viaarxiv icon

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

Add code
Mar 15, 2024
Figure 1 for CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Figure 2 for CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Figure 3 for CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Figure 4 for CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
Viaarxiv icon

End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context

Add code
Nov 01, 2023
Viaarxiv icon

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

Add code
Mar 28, 2023
Viaarxiv icon