CVNov 17, 2025
Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models
arXiv:2511.13276v1h-index: 6
Originality Incremental advance
AI Analysis
This addresses anomaly detection in surveillance for security applications, but it is incremental as it builds on existing weakly supervised methods.
The paper tackled detecting rare anomalies in surveillance videos with only video-level supervision, achieving 90.7% AUC on the UCF-Crime dataset.
We address the challenge of detecting rare and diverse anomalies in surveillance videos using only video-level supervision. Our dual-backbone framework combines convolutional and transformer representations through top-k pooling, achieving 90.7% area under the curve (AUC) on the UCF-Crime dataset.