mlsanityData to 14 Oct 2026

Overlooked Video Classification in Weakly Supervised Video Anomaly Detection

arXiv 2210.06688 ↗First posted 13 Oct 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Current weakly supervised video anomaly detection algorithms mostly use multiple instance learning (MIL) or their varieties. Almost all recent approaches focus on how to select the correct snippets for training to improve the performance. They overlook or do not realize the power of video classification in boosting the performance of anomaly detection. In this paper, we study explicitly the power of video classification supervision using a BERT or LSTM. With this BERT or LSTM, CNN features of all snippets of a video can be aggregated into a single feature which can be used for video classification. This simple yet powerful video classification supervision, combined into the MIL framework, brings extraordinary performance improvement on all three major video anomaly detection datasets. Particularly it improves the mean average precision (mAP) on the XD-Violence from SOTA 78.84% to new 82.10%. The source code is available at https://github.com/wjtan99/BERTAnomalyVideoClassification.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

20 of 30 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 637
  8. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  9. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  10. 2018Video Action Transformer Networkcited by 316
  11. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  12. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
8 more
  1. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  2. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  3. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  4. 2020Localizing Anomalies from Weakly-Labeled Videoscited by 52
  5. 2018An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videoscited by 45
  6. 2021Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Videocited by 32
  7. 2019Anomaly Locality in Video Surveillancecited by 18
  8. 2022Learning to Adapt to Unseen Abnormal Activities under Weak Supervisioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 0; 2026: 2.

6 papers.

  1. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  2. 2024Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detectioncited by 10
  3. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  4. 2024Multimodal Attention-Enhanced Feature Fusion-based Weekly Supervised Anomaly Violence Detectioncited by 2
  5. 2026Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidancecited by 1
  6. 2026Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluatedcited by 0