Just Dance with pi! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection

Snehashis Majhi; Giacomo D'Amicantonio; Antitza Dantcheva; Quan Kong; Lorenzo Garattoni; Gianpiero Francesca; Egor Bondarev; François Brémond

doi:10.1109/cvpr52734.2025.02260

CVPR2025顶会

Just Dance with pi! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection

Snehashis Majhi, Giacomo D'Amicantonio, Antitza Dantcheva, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, Egor Bondarev, François Brémond

DOI 出版方

2025年份

6顶会引用

摘要

Figure 1. a): Illustration of abnormal frames and respective multi-modal saliencies in complex real-world scenes. Optical flow captures distinct abnormal motion in "Abuse" and "Arrest", while depth and pose detect subtle movements that optical flow may miss. Panoptic masks and text provide overall scene context. b): Comparison of multi-modal methods with our PI-VAD. PI-VAD requires the five modalities only during training, significantly reducing computation and enabling real-world applicability.