Multi-modal skeleton action recognition method and device
The invention relates to the field of artificial intelligence visual language multi-modality, in particular to a multi-modality skeleton action recognition method and device. The method comprises the following steps: acquiring and preprocessing skeleton data, and extracting corresponding skeleton or...
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 | CHEN QIJUN LIU CHENGJU ZENG QINYANG |
| description | The invention relates to the field of artificial intelligence visual language multi-modality, in particular to a multi-modality skeleton action recognition method and device. The method comprises the following steps: acquiring and preprocessing skeleton data, and extracting corresponding skeleton original features; a visual encoder and a multi-layer perceptron are used for extracting corresponding visual features from the preprocessed skeleton data, meanwhile, a text prompt mapper is used for mapping action labels into texts, and a text encoder and the multi-layer perceptron are used for extracting corresponding language features from the texts; a loss value is calculated through a loss function, a visual encoder, a text decoder and a multi-layer perceptron are trained, and the loss function is composed of a visual loss function, a visual language loss function and a language decoding loss function; and testing by using the trained visual encoder to obtain a skeleton action recognition and classification resu |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117197891A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117197891A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117197891A3</originalsourceid><addsrcrecordid>eNrjZLD0Lc0pydTNzU9JzFEozk7NSS3Jz1NITC7JBFJFqcn56XmZYHZuaklGfopCYl6KQkpqWWZyKg8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzQ0N7Q0t7A0dDQmRg0AVtYu5Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multi-modal skeleton action recognition method and device</title><source>esp@cenet</source><creator>CHEN QIJUN ; LIU CHENGJU ; ZENG QINYANG</creator><creatorcontrib>CHEN QIJUN ; LIU CHENGJU ; ZENG QINYANG</creatorcontrib><description>The invention relates to the field of artificial intelligence visual language multi-modality, in particular to a multi-modality skeleton action recognition method and device. The method comprises the following steps: acquiring and preprocessing skeleton data, and extracting corresponding skeleton original features; a visual encoder and a multi-layer perceptron are used for extracting corresponding visual features from the preprocessed skeleton data, meanwhile, a text prompt mapper is used for mapping action labels into texts, and a text encoder and the multi-layer perceptron are used for extracting corresponding language features from the texts; a loss value is calculated through a loss function, a visual encoder, a text decoder and a multi-layer perceptron are trained, and the loss function is composed of a visual loss function, a visual language loss function and a language decoding loss function; and testing by using the trained visual encoder to obtain a skeleton action recognition and classification resu</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20231208&DB=EPODOC&CC=CN&NR=117197891A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231208&DB=EPODOC&CC=CN&NR=117197891A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN QIJUN</creatorcontrib><creatorcontrib>LIU CHENGJU</creatorcontrib><creatorcontrib>ZENG QINYANG</creatorcontrib><title>Multi-modal skeleton action recognition method and device</title><description>The invention relates to the field of artificial intelligence visual language multi-modality, in particular to a multi-modality skeleton action recognition method and device. The method comprises the following steps: acquiring and preprocessing skeleton data, and extracting corresponding skeleton original features; a visual encoder and a multi-layer perceptron are used for extracting corresponding visual features from the preprocessed skeleton data, meanwhile, a text prompt mapper is used for mapping action labels into texts, and a text encoder and the multi-layer perceptron are used for extracting corresponding language features from the texts; a loss value is calculated through a loss function, a visual encoder, a text decoder and a multi-layer perceptron are trained, and the loss function is composed of a visual loss function, a visual language loss function and a language decoding loss function; and testing by using the trained visual encoder to obtain a skeleton action recognition and classification resu</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLD0Lc0pydTNzU9JzFEozk7NSS3Jz1NITC7JBFJFqcn56XmZYHZuaklGfopCYl6KQkpqWWZyKg8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzQ0N7Q0t7A0dDQmRg0AVtYu5Q</recordid><startdate>20231208</startdate><enddate>20231208</enddate><creator>CHEN QIJUN</creator><creator>LIU CHENGJU</creator><creator>ZENG QINYANG</creator><scope>EVB</scope></search><sort><creationdate>20231208</creationdate><title>Multi-modal skeleton action recognition method and device</title><author>CHEN QIJUN ; LIU CHENGJU ; ZENG QINYANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117197891A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN QIJUN</creatorcontrib><creatorcontrib>LIU CHENGJU</creatorcontrib><creatorcontrib>ZENG QINYANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN QIJUN</au><au>LIU CHENGJU</au><au>ZENG QINYANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multi-modal skeleton action recognition method and device</title><date>2023-12-08</date><risdate>2023</risdate><abstract>The invention relates to the field of artificial intelligence visual language multi-modality, in particular to a multi-modality skeleton action recognition method and device. The method comprises the following steps: acquiring and preprocessing skeleton data, and extracting corresponding skeleton original features; a visual encoder and a multi-layer perceptron are used for extracting corresponding visual features from the preprocessed skeleton data, meanwhile, a text prompt mapper is used for mapping action labels into texts, and a text encoder and the multi-layer perceptron are used for extracting corresponding language features from the texts; a loss value is calculated through a loss function, a visual encoder, a text decoder and a multi-layer perceptron are trained, and the loss function is composed of a visual loss function, a visual language loss function and a language decoding loss function; and testing by using the trained visual encoder to obtain a skeleton action recognition and classification resu</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117197891A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Multi-modal skeleton action recognition method and device |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T14%3A18%3A04IST&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=CHEN%20QIJUN&rft.date=2023-12-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117197891A%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 |