Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
Authors:
Top Cited Papers
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4955-4966
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
All Related Versions
This publication has 57 references indexed in Scilit:
- Video anomaly detection based on locality sensitive hashing filtersPattern Recognition, 2016
- A Discriminative Framework for Anomaly Detection in Large Videos2016
- Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression2015
- Multiple instance learning for soft bags via top instances2015
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection2015
- Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contextsNeurocomputing, 2014
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Learning Fine-Grained Image Similarity with Deep Ranking2014
- Abnormal Event Detection at 150 FPS in MATLAB2013
- Event detection and analysis from video streamsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001