Anomize: Better Open Vocabulary Video Anomaly Detection
This addresses the challenge of detecting and classifying novel anomalies in video surveillance, which is an incremental improvement over existing methods.
The paper tackled the problem of open vocabulary video anomaly detection, where existing methods struggle with detection ambiguity and categorization confusion for novel anomalies, by proposing the Anomize framework that leverages supplementary visual and textual information with label relations, achieving superior performance on UCF-Crime and XD-Violence datasets.
Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-Crime and XD-Violence datasets, demonstrating its effectiveness in OVVAD.