# A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels

arXiv: https://arxiv.org/abs/2008.11887 · HTML: https://mlsanity.com/paper/2008.11887/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2110.09768/) (2021)
- [Towards Open Set Video Anomaly Detection](https://mlsanity.com/paper/2208.11113/) (2022)
- [Weakly Supervised Anomaly Detection: A Survey](https://mlsanity.com/paper/2302.04549/) (2023)
- [Video Anomaly Detection in 10 Years: A Survey and Outlook](https://mlsanity.com/paper/2405.19387/) (2024)
- [Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline](https://mlsanity.com/paper/2404.00847/) (2024)
- [Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies](https://mlsanity.com/paper/2203.13716/) (2022)
- [Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos](https://mlsanity.com/paper/2203.13704/) (2022)
- [Survey on video anomaly detection in dynamic scenes with moving cameras](https://mlsanity.com/paper/2308.07050/) (2023)
- [Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach](https://mlsanity.com/paper/2311.16514/) (2023)
- [Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos](https://mlsanity.com/paper/2202.06503/) (2022)
- [Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection](https://mlsanity.com/paper/2301.07923/) (2023)
- [Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey](https://mlsanity.com/paper/2412.00348/) (2024)
- [Deep Visual Anomaly detection with Negative Learning](https://mlsanity.com/paper/2105.11058/) (2021)
- [Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection](https://mlsanity.com/paper/2505.13123/) (2025)
- [Discriminative-Generative Dual Memory Video Anomaly Detection](https://mlsanity.com/paper/2104.14430/) (2021)
- [Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance](https://mlsanity.com/paper/2212.08506/) (2022)
- [Multimodal Attention-Enhanced Feature Fusion-based Weekly Supervised Anomaly Violence Detection](https://mlsanity.com/paper/2409.11223/) (2024)
- [A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection](https://mlsanity.com/paper/2310.05330/) (2023)
- [What Matters in Autonomous Driving Anomaly Detection: A Weakly Supervised Horizon](https://mlsanity.com/paper/2408.05562/) (2024)
- [RobustA: Robust Anomaly Detection in Multimodal Data](https://mlsanity.com/paper/2511.07276/) (2025)

## Abstract (arXiv)

Anomalous event detection in surveillance videos is a challenging and practical research problem among image and video processing community. Compared to the frame-level annotations of anomalous events, obtaining video-level annotations is quite fast and cheap though such high-level labels may contain significant noise. More specifically, an anomalous labeled video may actually contain anomaly only in a short duration while the rest of the video frames may be normal. In the current work, we propose a weakly supervised anomaly detection framework based on deep neural networks which is trained in a self-reasoning fashion using only video-level labels. To carry out the self-reasoning based training, we generate pseudo labels by using binary clustering of spatio-temporal video features which helps in mitigating the noise present in the labels of anomalous videos. Our proposed formulation encourages both the main network and the clustering to complement each other in achieving the goal of more accurate anomaly detection. The proposed framework has been evaluated on publicly available real-world anomaly detection datasets including UCF-crime, ShanghaiTech and UCSD Ped2. The experiments demonstrate superiority of our proposed framework over the current state-of-the-art methods.