Video Anomaly Detection with Structured Keywords
This work addresses efficient and interpretable anomaly detection for surveillance systems, though it is incremental with a performance trade-off against existing methods.
The paper tackles video anomaly detection by using structured keywords derived from foundational models to classify anomalies without temporal context, achieving ROC AUC scores of 0.865, 0.745, and 0.742 on UCSD Ped2, Shanghai Tech, and CUHK Avenue benchmarks.
This paper focuses on detecting anomalies in surveillance video using keywords by leveraging foundational models' feature representation generalization capabilities. We present a novel, lightweight pipeline for anomaly classification using keyword weights. Our pipeline employs a two-stage process: induction followed by deduction. In induction, descriptions are generated from normal and anomalous frames to identify and assign weights to relevant keywords. In deduction, inference frame descriptions are converted into keyword encodings using induction-derived weights for input into our neural network for anomaly classification. We achieved comparable performance on the three benchmarks UCSD Ped2, Shanghai Tech, and CUHK Avenue, with ROC AUC scores of 0.865, 0.745, and 0.742, respectively. These results are achieved without temporal context, making such a system viable for real-time applications. Our model improves implementation setup, interpretability, and inference speed for surveillance devices on the edge, introducing a performance trade-off against other video anomaly detection systems. As the generalization capabilities of open-source foundational models improve, our model demonstrates that the exclusive use of text for feature representations is a promising direction for efficient real-time interpretable video anomaly detection.