Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts
Gespeichert in:
| Titel: | Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts |
|---|---|
| Autoren: | Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, Peng Wang, Yanning Zhang |
| Quelle: | Proceedings of the 32nd ACM International Conference on Multimedia. :9301-9310 |
| Publication Status: | Preprint |
| Verlagsinformationen: | ACM, 2024. |
| Publikationsjahr: | 2024 |
| Schlagwörter: | FOS: Computer and information sciences, Scene anomaly detection, Visual content-based indexing and retrieval, Artificial Intelligence and Robotics, Artificial Intelligence (cs.AI), Spatio-temporal detection, Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Graphics and Human Computer Interfaces, Language-image pre-training, Computer Science - Computer Vision and Pattern Recognition, Video anomaly detection |
| Beschreibung: | 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. Accepted by ACMMM2024 |
| Publikationsart: | Article |
| Dateibeschreibung: | application/pdf |
| DOI: | 10.1145/3664647.3681442 |
| DOI: | 10.48550/arxiv.2408.05905 |
| Zugangs-URL: | http://arxiv.org/abs/2408.05905 |
| Rights: | arXiv Non-Exclusive Distribution CC BY NC ND URL: https://www.acm.org/publications/policies/copyright_policy#Background |
| Dokumentencode: | edsair.doi.dedup.....043e211c713029c1374e7fe9750d1b2c |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science | 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.<br />Accepted by ACMMM2024 |
|---|---|
| DOI: | 10.1145/3664647.3681442 |