GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Suhang, Peng, Xiaohao, Wang, Chong, Cai, Xiaojie, Qian, Jiangbo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909715829620736
author Cai, Suhang
Peng, Xiaohao
Wang, Chong
Cai, Xiaojie
Qian, Jiangbo
author_facet Cai, Suhang
Peng, Xiaohao
Wang, Chong
Cai, Xiaojie
Qian, Jiangbo
contents Video anomaly detection (VAD) plays a critical role in public safety applications such as intelligent surveillance. However, the rarity, unpredictability, and high annotation cost of real-world anomalies make it difficult to scale VAD datasets, which limits the performance and generalization ability of existing models. To address this challenge, we propose a generative video-enhanced weakly-supervised video anomaly detection (GV-VAD) framework that leverages text-conditioned video generation models to produce semantically controllable and physically plausible synthetic videos. These virtual videos are used to augment training data at low cost. In addition, a synthetic sample loss scaling strategy is utilized to control the influence of generated synthetic samples for efficient training. The experiments show that the proposed framework outperforms state-of-the-art methods on UCF-Crime datasets. The code is available at https://github.com/Sumutan/GV-VAD.git.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection
Cai, Suhang
Peng, Xiaohao
Wang, Chong
Cai, Xiaojie
Qian, Jiangbo
Computer Vision and Pattern Recognition
Artificial Intelligence
Video anomaly detection (VAD) plays a critical role in public safety applications such as intelligent surveillance. However, the rarity, unpredictability, and high annotation cost of real-world anomalies make it difficult to scale VAD datasets, which limits the performance and generalization ability of existing models. To address this challenge, we propose a generative video-enhanced weakly-supervised video anomaly detection (GV-VAD) framework that leverages text-conditioned video generation models to produce semantically controllable and physically plausible synthetic videos. These virtual videos are used to augment training data at low cost. In addition, a synthetic sample loss scaling strategy is utilized to control the influence of generated synthetic samples for efficient training. The experiments show that the proposed framework outperforms state-of-the-art methods on UCF-Crime datasets. The code is available at https://github.com/Sumutan/GV-VAD.git.
title GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.00312