mlsanityData to 14 Oct 2026

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv 2503.18094 ↗First posted 23 Mar 2025cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-Crime and XD-Violence datasets, demonstrating its effectiveness in OVVAD.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 41 of its 54 references that are in the map. First posted on arXiv 23 Mar 2025.

Builds on

41 of 54 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  8. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 565
  9. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  10. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  11. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 320
  12. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
29 more
  1. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 310
  2. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 300
  3. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  4. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  5. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  6. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  7. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  8. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  9. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  10. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  11. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  12. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  13. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  14. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  15. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  16. 2023Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimizationcited by 55
  17. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  18. 2023Global Knowledge Calibration for Fast Open-Vocabulary Segmentationcited by 40
  19. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  20. 2023Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Groundingcited by 32
  21. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  22. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  23. 2022Towards Open Set Video Anomaly Detectioncited by 26
  24. 2023Opening the Vocabulary of Egocentric Actionscited by 23
  25. 2023Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Datacited by 22
  26. 2024Retrieval-Augmented Open-Vocabulary Object Detectioncited by 20
  27. 2024XOV-Action: Towards Generalizable Open-Vocabulary Action Recognitioncited by 15
  28. 2023Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognitioncited by 8
  29. 2024Open-Vocabulary Spatio-Temporal Action Detectioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 10.

13 papers.

Sort:

By area:

  1. 2026No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detectioncited by 8
  2. 2025Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detectioncited by 4
  3. 2025Rethinking Metrics and Benchmarks of Video Anomaly Detectioncited by 3
  4. 2025Text-guided Fine-Grained Video Anomaly Understandingcited by 2
  5. 2026Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindnesscited by 2
  6. 2026ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitionscited by 1
  7. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Modelscited by 1
  8. 2026EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challengescited by 0
  9. 2026FoodMonitor: Benchmarking MLLMs for Explainable Compliance Analysiscited by 0
  10. 2026GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignmentcited by 0
  11. 2026NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detectioncited by 0
  12. 2026Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detectioncited by 0
1 more
  1. 2026Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimizationcited by 0