Guardado en:
Detalles Bibliográficos
Autores principales: Yin, Wenti, Zhang, Huaxin, Wang, Xiang, Lu, Yuqing, Zhang, Yicheng, Gong, Bingquan, Zuo, Jialong, Yu, Li, Gao, Changxin, Sang, Nong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.10334
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914156664324096
author Yin, Wenti
Zhang, Huaxin
Wang, Xiang
Lu, Yuqing
Zhang, Yicheng
Gong, Bingquan
Zuo, Jialong
Yu, Li
Gao, Changxin
Sang, Nong
author_facet Yin, Wenti
Zhang, Huaxin
Wang, Xiang
Lu, Yuqing
Zhang, Yicheng
Gong, Bingquan
Zuo, Jialong
Yu, Li
Gao, Changxin
Sang, Nong
contents Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances and classify categories. However, their objectives may tend to detect the most salient response segments, while neglecting to mine diverse normal patterns separated from anomalies, and are prone to category confusion due to similar appearance, leading to unsatisfactory fine-grained classification results. Therefore, we propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects, enhancing the distinguishability. Specifically, at the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes, encouraging the model to exploit normality cues inherent in the video, thereby improving the temporal separation of normal patterns and anomalous events. At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components using frame-level anomaly scores and then applies visual-language contrastive learning to enhance class-discriminative representations. Comprehensive experiments on two standard benchmarks, namely XD-Violence and UCF-Crime, demonstrate that DSANet outperforms existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10334
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
Yin, Wenti
Zhang, Huaxin
Wang, Xiang
Lu, Yuqing
Zhang, Yicheng
Gong, Bingquan
Zuo, Jialong
Yu, Li
Gao, Changxin
Sang, Nong
Computer Vision and Pattern Recognition
Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances and classify categories. However, their objectives may tend to detect the most salient response segments, while neglecting to mine diverse normal patterns separated from anomalies, and are prone to category confusion due to similar appearance, leading to unsatisfactory fine-grained classification results. Therefore, we propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects, enhancing the distinguishability. Specifically, at the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes, encouraging the model to exploit normality cues inherent in the video, thereby improving the temporal separation of normal patterns and anomalous events. At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components using frame-level anomaly scores and then applies visual-language contrastive learning to enhance class-discriminative representations. Comprehensive experiments on two standard benchmarks, namely XD-Violence and UCF-Crime, demonstrate that DSANet outperforms existing state-of-the-art methods.
title Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.10334