Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline
This addresses the need for more precise anomaly localization in surveillance and autonomous driving, though it appears incremental by building on existing object detection methods.
The paper tackles the problem of video anomaly detection by proposing a new framework called Track Any Anomalous Object (TAO), which integrates fine-grained anomalous object detection into a unified pipeline, achieving new benchmarks in accuracy and robustness.
Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing methods have primarily focused on detecting anomalous objects in videos -- either by identifying anomalous frames or objects -- they often neglect finer-grained analysis, such as anomalous pixels, which limits their ability to capture a broader range of anomalies. To address this challenge, we propose a new framework called Track Any Anomalous Object (TAO), which introduces a granular video anomaly detection pipeline that, for the first time, integrates the detection of multiple fine-grained anomalous objects into a unified framework. Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects. By linking anomaly scores to downstream tasks such as segmentation and tracking, our method removes the need for threshold tuning and achieves more precise anomaly localization in long and complex video sequences. Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness. Project page available online.