Skeleton action recognition method based on multi-center and multi-mode graph convolutional network
The invention discloses a skeleton action recognition method based on a multi-center and multi-mode graph convolutional network. The method comprises the following steps: step 1, obtaining skeleton data and carrying out data preprocessing and data enhancement; 2, taking the joint flow state of the s...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | ZHU CHONGLEI GUAN LIMING LIN HAIXIANG ZHANG HAIPING SHI YUELING ZHANG XINHAO |
| description | The invention discloses a skeleton action recognition method based on a multi-center and multi-mode graph convolutional network. The method comprises the following steps: step 1, obtaining skeleton data and carrying out data preprocessing and data enhancement; 2, taking the joint flow state of the skeleton data processed in the step 1 as first-order skeleton data; 3, processing the joint flow state to obtain second-order skeleton data, wherein the second-order skeleton data comprises a skeleton flow state; 4, applying a GPT-3 model, and taking the human body action recognition data as input to generate text description data of offline actions; step 5, constructing and training a multi-center multi-modal graph convolutional network model; and step 6, inputting and outputting the joint flow state data, the skeleton flow state data and the text description data into a final prediction result. According to the method, the network can conveniently identify and detect the object under extreme scale change, and atte |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118155283A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118155283A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118155283A3</originalsourceid><addsrcrecordid>eNqNjDEOgkAURGksjHqH7wEokJDQGoKxstGefHdHICz7yfLR6wuGA1i9mcnMbCNz7-Cg4omNtjMCjNS-_eke2oilJ4-wtPjJaRsbeEUg9nYNerGgOvDQkBH_Fjcta3bkoR8J3T7avNiNOKzcRcdL-SiuMQapMA48P0Kr4pYkeZJlpzw9p_90vuogPyE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Skeleton action recognition method based on multi-center and multi-mode graph convolutional network</title><source>esp@cenet</source><creator>ZHU CHONGLEI ; GUAN LIMING ; LIN HAIXIANG ; ZHANG HAIPING ; SHI YUELING ; ZHANG XINHAO</creator><creatorcontrib>ZHU CHONGLEI ; GUAN LIMING ; LIN HAIXIANG ; ZHANG HAIPING ; SHI YUELING ; ZHANG XINHAO</creatorcontrib><description>The invention discloses a skeleton action recognition method based on a multi-center and multi-mode graph convolutional network. The method comprises the following steps: step 1, obtaining skeleton data and carrying out data preprocessing and data enhancement; 2, taking the joint flow state of the skeleton data processed in the step 1 as first-order skeleton data; 3, processing the joint flow state to obtain second-order skeleton data, wherein the second-order skeleton data comprises a skeleton flow state; 4, applying a GPT-3 model, and taking the human body action recognition data as input to generate text description data of offline actions; step 5, constructing and training a multi-center multi-modal graph convolutional network model; and step 6, inputting and outputting the joint flow state data, the skeleton flow state data and the text description data into a final prediction result. According to the method, the network can conveniently identify and detect the object under extreme scale change, and atte</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</creationdate><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://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240607&DB=EPODOC&CC=CN&NR=118155283A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25555,76308</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240607&DB=EPODOC&CC=CN&NR=118155283A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHU CHONGLEI</creatorcontrib><creatorcontrib>GUAN LIMING</creatorcontrib><creatorcontrib>LIN HAIXIANG</creatorcontrib><creatorcontrib>ZHANG HAIPING</creatorcontrib><creatorcontrib>SHI YUELING</creatorcontrib><creatorcontrib>ZHANG XINHAO</creatorcontrib><title>Skeleton action recognition method based on multi-center and multi-mode graph convolutional network</title><description>The invention discloses a skeleton action recognition method based on a multi-center and multi-mode graph convolutional network. The method comprises the following steps: step 1, obtaining skeleton data and carrying out data preprocessing and data enhancement; 2, taking the joint flow state of the skeleton data processed in the step 1 as first-order skeleton data; 3, processing the joint flow state to obtain second-order skeleton data, wherein the second-order skeleton data comprises a skeleton flow state; 4, applying a GPT-3 model, and taking the human body action recognition data as input to generate text description data of offline actions; step 5, constructing and training a multi-center multi-modal graph convolutional network model; and step 6, inputting and outputting the joint flow state data, the skeleton flow state data and the text description data into a final prediction result. According to the method, the network can conveniently identify and detect the object under extreme scale change, and atte</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDEOgkAURGksjHqH7wEokJDQGoKxstGefHdHICz7yfLR6wuGA1i9mcnMbCNz7-Cg4omNtjMCjNS-_eke2oilJ4-wtPjJaRsbeEUg9nYNerGgOvDQkBH_Fjcta3bkoR8J3T7avNiNOKzcRcdL-SiuMQapMA48P0Kr4pYkeZJlpzw9p_90vuogPyE</recordid><startdate>20240607</startdate><enddate>20240607</enddate><creator>ZHU CHONGLEI</creator><creator>GUAN LIMING</creator><creator>LIN HAIXIANG</creator><creator>ZHANG HAIPING</creator><creator>SHI YUELING</creator><creator>ZHANG XINHAO</creator><scope>EVB</scope></search><sort><creationdate>20240607</creationdate><title>Skeleton action recognition method based on multi-center and multi-mode graph convolutional network</title><author>ZHU CHONGLEI ; GUAN LIMING ; LIN HAIXIANG ; ZHANG HAIPING ; SHI YUELING ; ZHANG XINHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118155283A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHU CHONGLEI</creatorcontrib><creatorcontrib>GUAN LIMING</creatorcontrib><creatorcontrib>LIN HAIXIANG</creatorcontrib><creatorcontrib>ZHANG HAIPING</creatorcontrib><creatorcontrib>SHI YUELING</creatorcontrib><creatorcontrib>ZHANG XINHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHU CHONGLEI</au><au>GUAN LIMING</au><au>LIN HAIXIANG</au><au>ZHANG HAIPING</au><au>SHI YUELING</au><au>ZHANG XINHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Skeleton action recognition method based on multi-center and multi-mode graph convolutional network</title><date>2024-06-07</date><risdate>2024</risdate><abstract>The invention discloses a skeleton action recognition method based on a multi-center and multi-mode graph convolutional network. The method comprises the following steps: step 1, obtaining skeleton data and carrying out data preprocessing and data enhancement; 2, taking the joint flow state of the skeleton data processed in the step 1 as first-order skeleton data; 3, processing the joint flow state to obtain second-order skeleton data, wherein the second-order skeleton data comprises a skeleton flow state; 4, applying a GPT-3 model, and taking the human body action recognition data as input to generate text description data of offline actions; step 5, constructing and training a multi-center multi-modal graph convolutional network model; and step 6, inputting and outputting the joint flow state data, the skeleton flow state data and the text description data into a final prediction result. According to the method, the network can conveniently identify and detect the object under extreme scale change, and atte</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118155283A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Skeleton action recognition method based on multi-center and multi-mode graph convolutional network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T00%3A29%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=ZHU%20CHONGLEI&rft.date=2024-06-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118155283A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |