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

Ex-VAD

Ex-VAD — LLM Knowledge Enhancement

ICML · 2025

Survey summary

Ex-VAD combines fine-grained anomaly classification with explanations: a VLM extracts frame-level captions that an LLM converts into video-level explanations, and a Label Augment and Alignment Module expands anomaly category labels into descriptive phrases for more precise detection.

Weakly Supervised

Weakly SupervisedLLM Knowledge Enhancement
Weakly SupervisedFrame captionsLLM explanationsLabel augmentation