Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sangeeta, Prajwal, Maddikuntla Sai, Dogra, Debi Prosad, Thakare, Kamalakar Vijay, Jung, Hyungjoo, Kim, Ig-Jae, Choi, Heeseung
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