Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2021

Abstract

Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing abnormal events, with each video represented as a bag of video snippets. Although current methods show effective detection performance, their recognition of the positive instances, i.e., rare abnormal snippets in the abnormal videos, is largely biased by the dominant negative instances, especially when the abnormal events are subtle anomalies that exhibit only small differences compared with normal events. This issue is exacerbated in many methods that ignore important video temporal dependencies. To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos. RTFM also adapts dilated convolutions and self-attention mechanisms to capture long- and short-range temporal dependencies to learn the feature magnitude more faithfully. Extensive experiments show that the RTFM-enabled MIL model (i) outperforms several state-of-the-art methods by a large margin on four benchmark data sets (ShanghaiTech, UCF-Crime, XD-Violence and UCSD-Peds) and (ii) achieves significantly improved subtle anomaly discriminability and sample efficiency.

Keywords

Vision applications and systems, Action and behavior recognition, Transfer/Low-shot/Semi/Unsupervised Learning

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

2021 18th IEEE/CVF International Conference on Computer Vision: Proceedings, Virtual, October 11-17

First Page

1

Last Page

13

ISBN

9781665428125

Identifier

10.1109/ICCV48922.2021.00493

Publisher

IEEE

City or Country

Piscataway, NJ

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/ICCV48922.2021.00493

Share

COinS