Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM

Weakly supervised video anomaly detection is a recent focus of computer vision research thanks to the availability of large-scale weakly supervised video datasets. However, most existing research works are limited to the frame-level classification with emphasis on finding the presence of specific ob...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhen Ma, José J. M. Machado, João Manuel R. S. Tavares
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	video anomaly detection three-dimensional convolution LSTM weakly supervised spatial-temporal features max-pooling Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/31e1f7c399464ec2869fff31068995ca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:31e1f7c399464ec2869fff31068995ca
record_format	dspace
spelling	oai:doaj.org-article:31e1f7c399464ec2869fff31068995ca2021-11-25T18:57:00ZWeakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM10.3390/s212275081424-8220https://doaj.org/article/31e1f7c399464ec2869fff31068995ca2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7508https://doaj.org/toc/1424-8220Weakly supervised video anomaly detection is a recent focus of computer vision research thanks to the availability of large-scale weakly supervised video datasets. However, most existing research works are limited to the frame-level classification with emphasis on finding the presence of specific objects or activities. In this article, a new neural network architecture is proposed to efficiently extract the prominent features for detecting whether a video contains anomalies. A video is treated as an integral input and the detection follows the procedure of video-label assignment. The extraction of spatial and temporal features is carried out by three-dimensional convolutions, and then their relationship is further modeled using an LSTM network. The concise structure of the proposed method enables high computational efficiency, and extensive experiments demonstrate its effectiveness.Zhen MaJosé J. M. MachadoJoão Manuel R. S. TavaresMDPI AGarticlevideo anomaly detectionthree-dimensional convolutionLSTMweakly supervisedspatial-temporal featuresmax-poolingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7508, p 7508 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	video anomaly detection three-dimensional convolution LSTM weakly supervised spatial-temporal features max-pooling Chemical technology TP1-1185
spellingShingle	video anomaly detection three-dimensional convolution LSTM weakly supervised spatial-temporal features max-pooling Chemical technology TP1-1185 Zhen Ma José J. M. Machado João Manuel R. S. Tavares Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
description	Weakly supervised video anomaly detection is a recent focus of computer vision research thanks to the availability of large-scale weakly supervised video datasets. However, most existing research works are limited to the frame-level classification with emphasis on finding the presence of specific objects or activities. In this article, a new neural network architecture is proposed to efficiently extract the prominent features for detecting whether a video contains anomalies. A video is treated as an integral input and the detection follows the procedure of video-label assignment. The extraction of spatial and temporal features is carried out by three-dimensional convolutions, and then their relationship is further modeled using an LSTM network. The concise structure of the proposed method enables high computational efficiency, and extensive experiments demonstrate its effectiveness.
format	article
author	Zhen Ma José J. M. Machado João Manuel R. S. Tavares
author_facet	Zhen Ma José J. M. Machado João Manuel R. S. Tavares
author_sort	Zhen Ma
title	Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
title_short	Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
title_full	Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
title_fullStr	Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
title_full_unstemmed	Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM
title_sort	weakly supervised video anomaly detection based on 3d convolution and lstm
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/31e1f7c399464ec2869fff31068995ca
work_keys_str_mv	AT zhenma weaklysupervisedvideoanomalydetectionbasedon3dconvolutionandlstm AT josejmmachado weaklysupervisedvideoanomalydetectionbasedon3dconvolutionandlstm AT joaomanuelrstavares weaklysupervisedvideoanomalydetectionbasedon3dconvolutionandlstm
_version_	1718410514249285632

Weakly Supervised Video Anomaly Detection Based on 3D Convolution and LSTM

Ejemplares similares