Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts

Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, PENG WANG, Yanning Zhang

Abstract: Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task.

Primary Subject Area: [Content] Media Interpretation

Secondary Subject Area: [Content] Vision and Language

Relevance To Conference: To our knowledge, our proposed STPrompt represents the first endeavor to efficiently transfer pre-trained vision-language knowledge from VLMs to simultaneously tackle video anomaly detection and localization (WSVADL). In summary, our work uses cross-modal alignment (i.e., Vision and Language) to address the WSVADL task, which conforms to the theme of Multimedia Content Understanding (Vision and Language, and Multimedia Interpretation).

Submission Number: 433