← Back to literature explorer
Weakly Supervised From survey PDF — verify links

VadCLIP

VadCLIP — Vision-Language Adaptation

AAAI · 2024

Survey summary

VadCLIP adapts frozen CLIP to weakly supervised VAD via a dual-branch design: one branch performs coarse-grained binary classification from visual features, the other exploits fine-grained vision-language alignment, achieving state-of-the-art results on UCF-Crime and XD-Violence.

Weakly Supervised

Weakly SupervisedVision-Language Adaptation
Weakly SupervisedCLIPDual-branchMIL-AlignLearnable prompts