Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection

TL;DR

This paper introduces a Bayesian nonparametric submodular video partition method that enhances multiple-instance learning for robust anomaly detection in videos, effectively handling outliers and diverse abnormal events.

Contribution

It proposes a novel Bayesian non-parametric hierarchical clustering approach that constructs a submodular set function to improve MIL training for video anomaly detection.

Findings

Demonstrated improved detection accuracy on multiple real-world datasets

Effectively handles outlier segments and multiple abnormal event types

Provides theoretical guarantees for the optimization algorithm

Abstract

Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually only available at the video level while missing for frames due to expensive labeling cost. We propose to conduct novel Bayesian non-parametric submodular video partition (BN-SVP) to significantly improve MIL model training that can offer a highly reliable solution for robust anomaly detection in practical settings that include outlier segments or multiple types of abnormal events. BN-SVP essentially performs dynamic non-parametric hierarchical clustering with an enhanced self-transition that groups segments in a video into temporally consistent and semantically coherent hidden states that can be naturally interpreted as scenes. Each segment is assumed to be generated through a non-parametric mixture process that allows variations of segments within the same scenes to accommodate the dynamic and noisy nature of many real-world surveillance videos. The scene and mixture component assignment of BN-SVP also induces a pairwise similarity among segments, resulting in non-parametric construction of a submodular set function. Integrating this function with an MIL loss effectively exposes the model to a diverse set of potentially positive instances to improve its training. A greedy algorithm is developed to optimize the submodular function and support efficient model training. Our theoretical analysis ensures a strong performance guarantee of the proposed algorithm. The effectiveness of the proposed approach is demonstrated over multiple real-world anomaly video datasets with robust detection performance.