VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection

Open paper

Benchmark	Model	Rank	Results
weakly-supervised-video-anomaly-detection-on-shanghaitech-weakly-supervised	VadCLIP	#5	AUC-ROC: 97.49
weakly-supervised-video-anomaly-detection-on-ubnormal	VadCLIP	#6	AUC-ROC: 62.32