Learning Event Completeness for Weakly Supervised Video Anomaly Detection

TL;DR

This paper introduces LEC-VAD, a novel weakly supervised video anomaly detection method that leverages semantic regularities and memory bank-based prototype learning to improve event localization and description, outperforming existing methods.

Contribution

The paper proposes a dual-structure model with semantic regularities and a memory bank mechanism to enhance event completeness and text expressiveness in WS-VAD.

Findings

Outperforms state-of-the-art on XD-Violence and UCF-Crime datasets

Uses anomaly-aware Gaussian mixture for precise event boundaries

Employs memory bank-based prototype learning to enrich text descriptions

Abstract

Weakly supervised video anomaly detection (WS-VAD) is tasked with pinpointing temporal intervals containing anomalous events within untrimmed videos, utilizing only video-level annotations. However, a significant challenge arises due to the absence of dense frame-level annotations, often leading to incomplete localization in existing WS-VAD methods. To address this issue, we present a novel LEC-VAD, Learning Event Completeness for Weakly Supervised Video Anomaly Detection, which features a dual structure designed to encode both category-aware and category-agnostic semantics between vision and language. Within LEC-VAD, we devise semantic regularities that leverage an anomaly-aware Gaussian mixture to learn precise event boundaries, thereby yielding more complete event instances. Besides, we develop a novel memory bank-based prototype learning mechanism to enrich concise text descriptions associated with anomaly-event categories. This innovation bolsters the text's expressiveness, which is crucial for advancing WS-VAD. Our LEC-VAD demonstrates remarkable advancements over the current state-of-the-art methods on two benchmark datasets XD-Violence and UCF-Crime.