mlsanityData to 14 Oct 2026

An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?

arXiv 2605.25806 ↗First posted 25 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Women's safety and security are paramount for a modern society. Often, crimes scenes get recorded through low-resolution CCTV cameras limiting the efficiency of video anomaly detection (VAD) models. Despite substantial progress in VAD research, women-centric anomalies are still underrepresented in datasets as well as in models. Existing datasets primarily cover well-lit, high-resolution and close-shot videos that are inadequate to tackle critical anomalies such as chain snatching, stalking, inappropriate touch, and other subtle forms of crime against women. To address this, we present a new benchmark, referred to as ExtrAnom. It contains 1001 videos (both anomalies and normal) with four textual annotations; one human-generated and three LLM-generated. The videos are arranged in 5 different categories of crimes. The dataset comprises low-light (8%), low-resolution (13%), long-shot (15%), and daytime (64%) anomaly videos. It includes stalking (3.9%), chain snatching (17.6%), kidnapping (7.3%), assassinations (2.3%), harassment (18.9%), and normal (50%) videos. It is possible to perform cross-modal and VLM-based validations using ExtrAnom. We have benchmarked it against popular unimodal and multi-modal VAD datasets (e.g., XD-Violence, UCF-Crime, and UCA) and SOTA methods. Experiments reveal that existing datasets are insufficient to deal with women-centric anomalies. We believe ExtrAnom can fill this critical gap in VAD research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 25 May 2026.

Builds on

22 of 39 references.

References · 22

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  6. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  8. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  9. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  10. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  11. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  12. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
10 more
  1. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 90
  2. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 87
  3. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 70
  4. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  5. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  6. 2023Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challengescited by 42
  7. 2019Anomaly Detection in Road Traffic Using Visual Surveillance: A Surveycited by 30
  8. 2022DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Networkcited by 26
  9. 2025Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detectioncited by 12
  10. 2024AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarioscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
  2. 2026Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models
  3. 2025AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
  4. 2024VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
  5. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
  6. 2024Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight
  7. 2025HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
  8. 2025A Benchmark for Crime Surveillance Video Analysis with Large Models