Online Anomaly Detection over Live Social Video Streaming

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: He, Chengkun, Zhou, Xiangmin, Wang, Chen, Gondal, Iqbal, Shao, Jie, Yi, Xun
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914643003310080
author He, Chengkun
Zhou, Xiangmin
Wang, Chen
Gondal, Iqbal
Shao, Jie
Yi, Xun
author_facet He, Chengkun
Zhou, Xiangmin
Wang, Chen
Gondal, Iqbal
Shao, Jie
Yi, Xun
contents Social video anomaly is an observation in video streams that does not conform to a common pattern of dataset's behaviour. Social video anomaly detection plays a critical role in applications from e-commerce to e-learning. Traditionally, anomaly detection techniques are applied to find anomalies in video broadcasting. However, they neglect the live social video streams which contain interactive talk, speech, or lecture with audience. In this paper, we propose a generic framework for effectively online detecting Anomalies Over social Video LIve Streaming (AOVLIS). Specifically, we propose a novel deep neural network model called Coupling Long Short-Term Memory (CLSTM) that adaptively captures the history behaviours of the presenters and audience, and their mutual interactions to predict their behaviour at next time point over streams. Then we well integrate the CLSTM with a decoder layer, and propose a new reconstruction error-based scoring function $RE_{IA}$ to calculate the anomaly score of each video segment for anomaly detection. After that, we propose a novel model update scheme that incrementally maintains CLSTM and decoder. Moreover, we design a novel upper bound and ADaptive Optimisation Strategy (ADOS) for improving the efficiency of our solution. Extensive experiments are conducted to prove the superiority of AOVLIS.
format Preprint
id arxiv_https___arxiv_org_abs_2401_08615
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Online Anomaly Detection over Live Social Video Streaming
He, Chengkun
Zhou, Xiangmin
Wang, Chen
Gondal, Iqbal
Shao, Jie
Yi, Xun
Computer Vision and Pattern Recognition
Social video anomaly is an observation in video streams that does not conform to a common pattern of dataset's behaviour. Social video anomaly detection plays a critical role in applications from e-commerce to e-learning. Traditionally, anomaly detection techniques are applied to find anomalies in video broadcasting. However, they neglect the live social video streams which contain interactive talk, speech, or lecture with audience. In this paper, we propose a generic framework for effectively online detecting Anomalies Over social Video LIve Streaming (AOVLIS). Specifically, we propose a novel deep neural network model called Coupling Long Short-Term Memory (CLSTM) that adaptively captures the history behaviours of the presenters and audience, and their mutual interactions to predict their behaviour at next time point over streams. Then we well integrate the CLSTM with a decoder layer, and propose a new reconstruction error-based scoring function $RE_{IA}$ to calculate the anomaly score of each video segment for anomaly detection. After that, we propose a novel model update scheme that incrementally maintains CLSTM and decoder. Moreover, we design a novel upper bound and ADaptive Optimisation Strategy (ADOS) for improving the efficiency of our solution. Extensive experiments are conducted to prove the superiority of AOVLIS.
title Online Anomaly Detection over Live Social Video Streaming
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.08615