Attention-driven pseudo-label self-training for weakly supervised video anomaly detection
Top Cited Papers
- 28 February 2026
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 177
Abstract
No abstract availableFunding Information
- Key Technologies Research and Development Program of Guangzhou Municipality (202206030003)
- National Natural Science Foundation of China (62471371)
This publication has 15 references indexed in Scilit:
- Video Anomaly Detection via self-supervised and spatio-temporal proxy tasks learningPattern Recognition, 2024
- Semantic-driven dual consistency learning for weakly supervised video anomaly detectionPattern Recognition, 2024
- Video anomaly detection guided by clustering learningPattern Recognition, 2024
- Weakly-Supervised Video Anomaly Detection With Snippet Anomalous AttentionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Adversarial and focused training of abnormal videos for weakly-supervised anomaly detectionPattern Recognition, 2023
- Rethinking Attentive Object Detection via Neural Attention LearningIEEE Transactions on Image Processing, 2023
- Weakly Supervised Video Anomaly Detection via Self-Guided Temporal Discriminative TransformerIEEE Transactions on Cybernetics, 2022
- Localizing Anomalies From Weakly-Labeled VideosIEEE Transactions on Image Processing, 2021
- Learning Causal Temporal Relation and Feature Discrimination for Anomaly DetectionIEEE Transactions on Image Processing, 2021
- Robust visual tracking via scale-and-state-awarenessNeurocomputing, 2019