AI RESEARCH
EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges
arXiv CS.CV
•
ArXi:2604.22595v1 Announce Type: new CLIP has nstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most existing approaches that adapt CLIP for action recognition have primarily focused on temporal modeling, often overlooking spatial perception. In real-world scenarios, visual challenges such as low-light environments or egocentric viewpoints can severely impair spatial understanding, an essential precursor for effective temporal reasoning.