# Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

arXiv: https://arxiv.org/abs/2212.04090 · HTML: https://mlsanity.com/paper/2212.04090/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection](https://mlsanity.com/paper/2011.12077/) (2020)
- [Learning Deep Representations of Appearance and Motion for Anomalous Event Detection](https://mlsanity.com/paper/1510.01553/) (2015)
- [Abnormal Event Detection in Videos using Spatiotemporal Autoencoder](https://mlsanity.com/paper/1701.01546/) (2017)
- [Localizing Anomalies from Weakly-Labeled Videos](https://mlsanity.com/paper/2008.08944/) (2020)
- [Motion-Aware Feature for Improved Video Anomaly Detection](https://mlsanity.com/paper/1907.10211/) (2019)
- [Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection](https://mlsanity.com/paper/2203.12840/) (2022)
- [Motion-Augmented Self-Training for Video Recognition at Smaller Scale](https://mlsanity.com/paper/2105.01646/) (2021)

## Built on by (most cited first, 30 of 47)

- [Open-Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2311.07042/) (2023)
- [Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2404.08531/) (2024)
- [Video Anomaly Detection and Explanation via Large Language Models](https://mlsanity.com/paper/2401.05702/) (2024)
- [Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2306.14451/) (2023)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [Open-World Semantic Segmentation Including Class Similarity](https://mlsanity.com/paper/2403.07532/) (2024)
- [VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models](https://mlsanity.com/paper/2412.01095/) (2024)
- [TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection](https://mlsanity.com/paper/2308.11072/) (2023)
- [BatchNorm-based Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2311.15367/) (2023)
- [Video Anomaly Detection in 10 Years: A Survey and Outlook](https://mlsanity.com/paper/2405.19387/) (2024)
- [VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree](https://mlsanity.com/paper/2510.22693/) (2025)
- [Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline](https://mlsanity.com/paper/2404.00847/) (2024)
- [Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention](https://mlsanity.com/paper/2309.16309/) (2023)
- [Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space](https://mlsanity.com/paper/2305.18797/) (2023)
- [Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach](https://mlsanity.com/paper/2311.16514/) (2023)
- [Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2412.20455/) (2024)
- [AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection](https://mlsanity.com/paper/2504.04495/) (2025)
- [Cross-Domain Learning for Video Anomaly Detection with Limited Supervision](https://mlsanity.com/paper/2408.05191/) (2024)
- [Vision-Language Models Assisted Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2409.14109/) (2024)
- [Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection](https://mlsanity.com/paper/2412.03044/) (2024)
- [Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2508.06318/) (2025)
- [Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2401.13551/) (2024)
- [Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method](https://mlsanity.com/paper/2501.07496/) (2025)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment](https://mlsanity.com/paper/2508.14203/) (2025)
- [Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection](https://mlsanity.com/paper/2405.05130/) (2024)
- [Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection](https://mlsanity.com/paper/2505.13123/) (2025)
- [Learning Event Completeness for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2506.13095/) (2025)
- [Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning](https://mlsanity.com/paper/2603.00550/) (2026)
- [Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection](https://mlsanity.com/paper/2403.01169/) (2024)

## Abstract (arXiv)

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.