Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.25806 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918521488801792 |
|---|---|
| author | Sangeeta Prajwal, Maddikuntla Sai Dogra, Debi Prosad Thakare, Kamalakar Vijay Jung, Hyungjoo Kim, Ig-Jae Choi, Heeseung |
| author_facet | Sangeeta Prajwal, Maddikuntla Sai Dogra, Debi Prosad Thakare, Kamalakar Vijay Jung, Hyungjoo Kim, Ig-Jae Choi, Heeseung |
| contents | Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, such events are captured through real-world surveillance cameras that operate at lower resolutions. Despite substantial progress in CV-related research, video anomaly detection (VAD) focused on women's safety has not yet been adequately addressed. Existing video anomaly datasets contain well-lit, high-resolution, close-shot videos, and fail to represent women-centric anomalies such as chain snatching, stalking, inappropriate touch, and other subtle forms of crime against women. To address these problems, we propose the ExtrAnom dataset, a new multi-modal benchmark containing 1001 videos with textual descriptions, 500 normal and 501 anomalous, classified into 5 different types of women-centric crimes. The dataset comprises low-light (8%), low-resolution videos (13%), long-shot (15%), along with daylight (64%) anomalous videos. And it covers anomalous events like stalking (3.9%), chain snatching (17.6%), kidnapping (7.3%), assassinations (2.3%), harassment (18.9%), and normal (50%). Each video is supplemented with 4 textual annotations, including one human-generated and three LLM-generated descriptions, enabling cross-modal and VLM-based validations. The aim of creating a women-centric dataset is to accurately detect the women-centric anomaly patterns, which are possible to observe visually. The dataset supplements the VLMs to accurately generate video-level descriptions. ExtrAnom has been benchmarked against popular unimodal and multi-modal VAD datasets (e.g., XD-Violence, UCF-Crime, and UCA) and SOTA methods. Experiments reveal that the existing datasets are insufficient to train models for detecting women-centric anomalies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25806 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset? Sangeeta Prajwal, Maddikuntla Sai Dogra, Debi Prosad Thakare, Kamalakar Vijay Jung, Hyungjoo Kim, Ig-Jae Choi, Heeseung Computer Vision and Pattern Recognition Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, such events are captured through real-world surveillance cameras that operate at lower resolutions. Despite substantial progress in CV-related research, video anomaly detection (VAD) focused on women's safety has not yet been adequately addressed. Existing video anomaly datasets contain well-lit, high-resolution, close-shot videos, and fail to represent women-centric anomalies such as chain snatching, stalking, inappropriate touch, and other subtle forms of crime against women. To address these problems, we propose the ExtrAnom dataset, a new multi-modal benchmark containing 1001 videos with textual descriptions, 500 normal and 501 anomalous, classified into 5 different types of women-centric crimes. The dataset comprises low-light (8%), low-resolution videos (13%), long-shot (15%), along with daylight (64%) anomalous videos. And it covers anomalous events like stalking (3.9%), chain snatching (17.6%), kidnapping (7.3%), assassinations (2.3%), harassment (18.9%), and normal (50%). Each video is supplemented with 4 textual annotations, including one human-generated and three LLM-generated descriptions, enabling cross-modal and VLM-based validations. The aim of creating a women-centric dataset is to accurately detect the women-centric anomaly patterns, which are possible to observe visually. The dataset supplements the VLMs to accurately generate video-level descriptions. ExtrAnom has been benchmarked against popular unimodal and multi-modal VAD datasets (e.g., XD-Violence, UCF-Crime, and UCA) and SOTA methods. Experiments reveal that the existing datasets are insufficient to train models for detecting women-centric anomalies. |
| title | An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.25806 |