TrCLIP-VAD : Weak supervised video anomaly detection by improving CLIP training with text rewriting
- 8 April 2026
- journal article
- Published by Elsevier in Neural Networks
- Vol. 201, 108951
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62472368)
- National Natural Science Foundation of China (62302427)
- Science and Technology Department of Xinjiang Uyghur Autonomous Region (2022TSYCLJ0036)
- Ministry of Science and Technology of the People's Republic of China (2022ZD0115800)
- Xinjiang University (XJDX2025YJS181)
This publication has 14 references indexed in Scilit:
- VADMamba: Exploring State Space Models for Fast Video Anomaly Detection2025
- Prototype-guided and dynamic-aware video anomaly detectionNeural Networks, 2025
- MSTAgent-VAD: Multi-scale video anomaly detection using time agent mechanism for segments’ temporal context miningExpert Systems with Applications, 2025
- BatchNorm-Based Weakly Supervised Video Anomaly DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- An informative dual ForkNet for video anomaly detectionNeural Networks, 2024
- Cross-modality integration framework with prediction, perception and discrimination for video anomaly detectionNeural Networks, 2024
- Automated anomaly detection and multi-label anomaly classification in crowd scenes based on optimal thresholding and deep learning strategyInternational Journal of Autonomous and Adaptive Communications Systems, 2024
- IoT-based vehicular accident detection using a deep learning modelInternational Journal of Autonomous and Adaptive Communications Systems, 2024
- Learning to Prompt for Vision-Language ModelsInternational Journal of Computer Vision, 2022
- Weakly Supervised Audio-Visual Violence DetectionIEEE Transactions on Multimedia, 2022