A Comprehensive Survey on Geometric Deep Learning

Deep learning methods have achieved great success in analyzing traditional data such as texts, sounds, images and videos. More and more research works are carrying out to extend standard deep learning technologies to geometric data such as point cloud or voxel grid of 3D objects, real life networks...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenming Cao, Zhiyue Yan, Zhiquan He, Zhihai He
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Convolutional neural networks geometric deep learning graph manifold Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/e1cb6cbf17ab4b4297162006519663a3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e1cb6cbf17ab4b4297162006519663a3
record_format	dspace
spelling	oai:doaj.org-article:e1cb6cbf17ab4b4297162006519663a32021-11-19T00:03:47ZA Comprehensive Survey on Geometric Deep Learning2169-353610.1109/ACCESS.2020.2975067https://doaj.org/article/e1cb6cbf17ab4b4297162006519663a32020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9003285/https://doaj.org/toc/2169-3536Deep learning methods have achieved great success in analyzing traditional data such as texts, sounds, images and videos. More and more research works are carrying out to extend standard deep learning technologies to geometric data such as point cloud or voxel grid of 3D objects, real life networks such as social and citation network. Many methods have been proposed in the research area. In this work, we aim to provide a comprehensive survey of geometric deep learning and related methods. First, we introduce the relevant knowledge and history of geometric deep learning field as well as the theoretical background. In the method part, we review different graph network models for graphs and manifold data. Besides, practical applications of these methods, datasets currently available in different research area and the problems and challenges are also summarized.Wenming CaoZhiyue YanZhiquan HeZhihai HeIEEEarticleConvolutional neural networksgeometric deep learninggraphmanifoldElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 35929-35949 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Convolutional neural networks geometric deep learning graph manifold Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Convolutional neural networks geometric deep learning graph manifold Electrical engineering. Electronics. Nuclear engineering TK1-9971 Wenming Cao Zhiyue Yan Zhiquan He Zhihai He A Comprehensive Survey on Geometric Deep Learning
description	Deep learning methods have achieved great success in analyzing traditional data such as texts, sounds, images and videos. More and more research works are carrying out to extend standard deep learning technologies to geometric data such as point cloud or voxel grid of 3D objects, real life networks such as social and citation network. Many methods have been proposed in the research area. In this work, we aim to provide a comprehensive survey of geometric deep learning and related methods. First, we introduce the relevant knowledge and history of geometric deep learning field as well as the theoretical background. In the method part, we review different graph network models for graphs and manifold data. Besides, practical applications of these methods, datasets currently available in different research area and the problems and challenges are also summarized.
format	article
author	Wenming Cao Zhiyue Yan Zhiquan He Zhihai He
author_facet	Wenming Cao Zhiyue Yan Zhiquan He Zhihai He
author_sort	Wenming Cao
title	A Comprehensive Survey on Geometric Deep Learning
title_short	A Comprehensive Survey on Geometric Deep Learning
title_full	A Comprehensive Survey on Geometric Deep Learning
title_fullStr	A Comprehensive Survey on Geometric Deep Learning
title_full_unstemmed	A Comprehensive Survey on Geometric Deep Learning
title_sort	comprehensive survey on geometric deep learning
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/e1cb6cbf17ab4b4297162006519663a3
work_keys_str_mv	AT wenmingcao acomprehensivesurveyongeometricdeeplearning AT zhiyueyan acomprehensivesurveyongeometricdeeplearning AT zhiquanhe acomprehensivesurveyongeometricdeeplearning AT zhihaihe acomprehensivesurveyongeometricdeeplearning AT wenmingcao comprehensivesurveyongeometricdeeplearning AT zhiyueyan comprehensivesurveyongeometricdeeplearning AT zhiquanhe comprehensivesurveyongeometricdeeplearning AT zhihaihe comprehensivesurveyongeometricdeeplearning
_version_	1718420700867330048

A Comprehensive Survey on Geometric Deep Learning

Ejemplares similares