Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-02
Main Authors: Wang, Shengqin, Zhang, Yongji, Hong, Qi, Zhao, Minghao, Jiang, Yu
Format: Article
Language:English
Subjects:
Activity recognition
Data integration
Graph theory
Time dependence
Topology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Wang, Shengqin
Zhang, Yongji
Hong, Qi
Zhao, Minghao
Jiang, Yu
description Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This paper proposes a dynamic spatial-temporal hypergraph convolutional network (DST-HCN) to capture spatial-temporal information for skeleton-based action recognition. DST-HCN introduces a time-point hypergraph (TPH) to learn relationships at time points. With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features. In addition, we use the high-order information fusion module (HIF) to fuse spatial-temporal information synchronously. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets show that our model achieves state-of-the-art, especially compared with hypergraph methods.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2778134905</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2778134905</sourcerecordid><originalsourceid>FETCH-proquest_journals_27781349053</originalsourceid><addsrcrecordid>eNqNjNEKgjAYRkcQJNU7DLoWdMu0y7DCqy6ye1n2a-rcv7ZZ9PYl9ABdfQfO4ZsQj3Ee-smasRlZWtsGQcA2MYsi7pFi_1aib0qaa-EaIX0HvUYjJM3eGkxthL7TFNUT5eAaVF9xAvdC09EKDc07kOBQ-Vdh4UZ35djQM5RYq2bkBZlWQlpY_nZOVsfDJc18bfAxgHVFi4P53tqCxXES8vU2iPh_1QceSEVs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2778134905</pqid></control><display><type>article</type><title>Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition</title><source>Publicly Available Content Database</source><creator>Wang, Shengqin ; Zhang, Yongji ; Hong, Qi ; Zhao, Minghao ; Jiang, Yu</creator><creatorcontrib>Wang, Shengqin ; Zhang, Yongji ; Hong, Qi ; Zhao, Minghao ; Jiang, Yu</creatorcontrib><description>Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This paper proposes a dynamic spatial-temporal hypergraph convolutional network (DST-HCN) to capture spatial-temporal information for skeleton-based action recognition. DST-HCN introduces a time-point hypergraph (TPH) to learn relationships at time points. With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features. In addition, we use the high-order information fusion module (HIF) to fuse spatial-temporal information synchronously. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets show that our model achieves state-of-the-art, especially compared with hypergraph methods.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Activity recognition ; Data integration ; Graph theory ; Time dependence ; Topology</subject><ispartof>arXiv.org, 2023-02</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2778134905?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Wang, Shengqin</creatorcontrib><creatorcontrib>Zhang, Yongji</creatorcontrib><creatorcontrib>Hong, Qi</creatorcontrib><creatorcontrib>Zhao, Minghao</creatorcontrib><creatorcontrib>Jiang, Yu</creatorcontrib><title>Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition</title><title>arXiv.org</title><description>Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This paper proposes a dynamic spatial-temporal hypergraph convolutional network (DST-HCN) to capture spatial-temporal information for skeleton-based action recognition. DST-HCN introduces a time-point hypergraph (TPH) to learn relationships at time points. With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features. In addition, we use the high-order information fusion module (HIF) to fuse spatial-temporal information synchronously. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets show that our model achieves state-of-the-art, especially compared with hypergraph methods.</description><subject>Activity recognition</subject><subject>Data integration</subject><subject>Graph theory</subject><subject>Time dependence</subject><subject>Topology</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjNEKgjAYRkcQJNU7DLoWdMu0y7DCqy6ye1n2a-rcv7ZZ9PYl9ABdfQfO4ZsQj3Ee-smasRlZWtsGQcA2MYsi7pFi_1aib0qaa-EaIX0HvUYjJM3eGkxthL7TFNUT5eAaVF9xAvdC09EKDc07kOBQ-Vdh4UZ35djQM5RYq2bkBZlWQlpY_nZOVsfDJc18bfAxgHVFi4P53tqCxXES8vU2iPh_1QceSEVs</recordid><startdate>20230217</startdate><enddate>20230217</enddate><creator>Wang, Shengqin</creator><creator>Zhang, Yongji</creator><creator>Hong, Qi</creator><creator>Zhao, Minghao</creator><creator>Jiang, Yu</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230217</creationdate><title>Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition</title><author>Wang, Shengqin ; Zhang, Yongji ; Hong, Qi ; Zhao, Minghao ; Jiang, Yu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27781349053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Activity recognition</topic><topic>Data integration</topic><topic>Graph theory</topic><topic>Time dependence</topic><topic>Topology</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Shengqin</creatorcontrib><creatorcontrib>Zhang, Yongji</creatorcontrib><creatorcontrib>Hong, Qi</creatorcontrib><creatorcontrib>Zhao, Minghao</creatorcontrib><creatorcontrib>Jiang, Yu</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Shengqin</au><au>Zhang, Yongji</au><au>Hong, Qi</au><au>Zhao, Minghao</au><au>Jiang, Yu</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition</atitle><jtitle>arXiv.org</jtitle><date>2023-02-17</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This paper proposes a dynamic spatial-temporal hypergraph convolutional network (DST-HCN) to capture spatial-temporal information for skeleton-based action recognition. DST-HCN introduces a time-point hypergraph (TPH) to learn relationships at time points. With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features. In addition, we use the high-order information fusion module (HIF) to fuse spatial-temporal information synchronously. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets show that our model achieves state-of-the-art, especially compared with hypergraph methods.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2778134905
source Publicly Available Content Database
subjects Activity recognition
Data integration
Graph theory
Time dependence
Topology
title Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T21%3A00%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Dynamic%20Spatial-temporal%20Hypergraph%20Convolutional%20Network%20for%20Skeleton-based%20Action%20Recognition&rft.jtitle=arXiv.org&rft.au=Wang,%20Shengqin&rft.date=2023-02-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2778134905%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_27781349053%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2778134905&rft_id=info:pmid/&rfr_iscdi=true