Picture for Gangshan Wu

Gangshan Wu

Efficient Test-Time Prompt Tuning for Vision-Language Models

Add code
Aug 11, 2024
Figure 1 for Efficient Test-Time Prompt Tuning for Vision-Language Models
Figure 2 for Efficient Test-Time Prompt Tuning for Vision-Language Models
Figure 3 for Efficient Test-Time Prompt Tuning for Vision-Language Models
Figure 4 for Efficient Test-Time Prompt Tuning for Vision-Language Models
Viaarxiv icon

RAVSS: Robust Audio-Visual Speech Separation in Multi-Speaker Scenarios with Missing Visual Cues

Add code
Jul 27, 2024
Viaarxiv icon

GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation

Add code
Jul 16, 2024
Viaarxiv icon

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

Add code
Jul 05, 2024
Viaarxiv icon

Open-Vocabulary Spatio-Temporal Action Detection

Add code
May 17, 2024
Viaarxiv icon

SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos

Add code
Apr 06, 2024
Viaarxiv icon

Dual DETRs for Multi-Label Temporal Action Detection

Add code
Mar 31, 2024
Viaarxiv icon

Spatiotemporal Predictive Pre-training for Robotic Motor Control

Add code
Mar 14, 2024
Viaarxiv icon

Sketch and Refine: Towards Fast and Accurate Lane Detection

Add code
Jan 26, 2024
Viaarxiv icon

Asymmetric Masked Distillation for Pre-Training Small Foundation Models

Add code
Nov 06, 2023
Viaarxiv icon