mlsanityData to 14 Oct 2026

Consistency-based Self-supervised Learning for Temporal Anomaly Localization

arXiv 2208.05251 ↗First posted 10 Aug 2022cs.CV cs.AI cs.MMcited by 10

Not on the map. Why?

Abstract (arXiv)

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization of anomalous activities within the video stream: this is a very challenging scenario, as training examples come only with video-level annotations (and not frame-level). Several recent works have proposed various regularization terms to address it i.e. by enforcing sparsity and smoothness constraints over the weakly-learned frame-level anomaly scores. In this work, we get inspired by recent advances within the field of self-supervised learning and ask the model to yield the same scores for different augmentations of the same video sequence. We show that enforcing such an alignment improves the performance of the model on XD-Violence.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 10 Aug 2022.

Builds on

39 of 55 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  7. 2017The Kinetics Human Action Video Datasetcited by 1,909
  8. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  9. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  10. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  11. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  12. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 329
27 more
  1. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  2. 2016Learning Temporal Regularity in Video Sequencescited by 254
  3. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  4. 2015Beyond Short Snippets: Deep Networks for Video Classificationcited by 233
  5. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  6. 2019Graph Convolutional Networks for Temporal Action Localizationcited by 208
  7. 2018Rethinking the Faster R-CNN Architecture for Temporal Action Localizationcited by 194
  8. 2017R-C3D: Region Convolutional 3D Network for Temporal Activity Detectioncited by 161
  9. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  10. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  11. 2019Gaussian Temporal Awareness Networks for Action Localizationcited by 135
  12. 2017UntrimmedNets for Weakly Supervised Action Recognition and Detectioncited by 130
  13. 2017Single Shot Temporal Action Detectioncited by 123
  14. 2017TURN TAP: Temporal Unit Regression Network for Temporal Action Proposalscited by 113
  15. 2017Weakly Supervised Action Localization by Sparse Temporal Pooling Networkcited by 100
  16. 2018AutoLoc: Weakly-supervised Temporal Action Localizationcited by 75
  17. 2020Revisiting Anchor Mechanisms for Temporal Action Localizationcited by 75
  18. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  19. 2020Localizing Anomalies from Weakly-Labeled Videoscited by 52
  20. 2019Motion-Aware Feature for Improved Video Anomaly Detectioncited by 48
  21. 2020Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Predictioncited by 42
  22. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  23. 2021Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Videocited by 32
  24. 2021Continual Semi-Supervised Learning through Contrastive Interpolation Consistencycited by 25
  25. 2016Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networkscited by 24
  26. 2019Spotting insects from satellites: modeling the presence of Culicoides imicola through Deep CNNscited by 4
  27. 2021The Role of the Input in Natural Language Video Descriptioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 2; 2026: 1.

10 papers.

  1. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  2. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  3. 2023Volumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyricited by 2
  4. 2024Learn Suspected Anomalies from Event Prompts for Video Anomaly Detectioncited by 2
  5. 2024Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learningcited by 2
  6. 2023Deep Neural Networks in Video Human Action Recognition: A Reviewcited by 1
  7. 2023Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinitycited by 0
  8. 2025HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detectioncited by 0
  9. 2025GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detectioncited by 0
  10. 2026Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluatedcited by 0