Training method of video behavior recognition model, and video behavior recognition method and device

Training method of video behavior recognition model, and video behavior recognition method and device

The invention provides a training method of a video behavior recognition model, and a video behavior recognition method and device. A specific embodiment of the method comprises the steps of inputting a sample image sequence corresponding to a sample video stream into an initial behavior recognition...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: DONG SHUAI, YE RUNYUAN, ZOU KUN, FENG ZIJU, LI WENSHENG, XIONG KUNKUN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
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 DONG SHUAI
YE RUNYUAN
ZOU KUN
FENG ZIJU
LI WENSHENG
XIONG KUNKUN
description The invention provides a training method of a video behavior recognition model, and a video behavior recognition method and device. A specific embodiment of the method comprises the steps of inputting a sample image sequence corresponding to a sample video stream into an initial behavior recognition model; the sample video stream comprises a source domain sample video stream and a target domain sample video stream; the initial behavior recognition model comprises a classifier and a plurality of domain discriminators; aligning the features of the sample image sequence on different scales by using the plurality of domain discriminators to obtain a domain discrimination result; and training the initial behavior recognition model based on a classification result output by the classifier for the source domain sample video stream and domain discrimination results output by the plurality of domain discriminators. According to the method, the difference between the source domain sample video data and the target domai
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116758370A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116758370A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116758370A3</originalsourceid><addsrcrecordid>eNrjZEgNKUrMzMvMS1fITS3JyE9RyE9TKMtMSc1XSErNSCzLzC9SKEpNzk_PyyzJzM9TyM1PSc3RUUjMS8GrCmIUSFVKallmcioPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NDM3tTA2N3A0JkYNACKSPy4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Training method of video behavior recognition model, and video behavior recognition method and device</title><source>esp@cenet</source><creator>DONG SHUAI ; YE RUNYUAN ; ZOU KUN ; FENG ZIJU ; LI WENSHENG ; XIONG KUNKUN</creator><creatorcontrib>DONG SHUAI ; YE RUNYUAN ; ZOU KUN ; FENG ZIJU ; LI WENSHENG ; XIONG KUNKUN</creatorcontrib><description>The invention provides a training method of a video behavior recognition model, and a video behavior recognition method and device. A specific embodiment of the method comprises the steps of inputting a sample image sequence corresponding to a sample video stream into an initial behavior recognition model; the sample video stream comprises a source domain sample video stream and a target domain sample video stream; the initial behavior recognition model comprises a classifier and a plurality of domain discriminators; aligning the features of the sample image sequence on different scales by using the plurality of domain discriminators to obtain a domain discrimination result; and training the initial behavior recognition model based on a classification result output by the classifier for the source domain sample video stream and domain discrimination results output by the plurality of domain discriminators. According to the method, the difference between the source domain sample video data and the target domai</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&amp;date=20230915&amp;DB=EPODOC&amp;CC=CN&amp;NR=116758370A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230915&amp;DB=EPODOC&amp;CC=CN&amp;NR=116758370A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DONG SHUAI</creatorcontrib><creatorcontrib>YE RUNYUAN</creatorcontrib><creatorcontrib>ZOU KUN</creatorcontrib><creatorcontrib>FENG ZIJU</creatorcontrib><creatorcontrib>LI WENSHENG</creatorcontrib><creatorcontrib>XIONG KUNKUN</creatorcontrib><title>Training method of video behavior recognition model, and video behavior recognition method and device</title><description>The invention provides a training method of a video behavior recognition model, and a video behavior recognition method and device. A specific embodiment of the method comprises the steps of inputting a sample image sequence corresponding to a sample video stream into an initial behavior recognition model; the sample video stream comprises a source domain sample video stream and a target domain sample video stream; the initial behavior recognition model comprises a classifier and a plurality of domain discriminators; aligning the features of the sample image sequence on different scales by using the plurality of domain discriminators to obtain a domain discrimination result; and training the initial behavior recognition model based on a classification result output by the classifier for the source domain sample video stream and domain discrimination results output by the plurality of domain discriminators. According to the method, the difference between the source domain sample video data and the target domai</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZEgNKUrMzMvMS1fITS3JyE9RyE9TKMtMSc1XSErNSCzLzC9SKEpNzk_PyyzJzM9TyM1PSc3RUUjMS8GrCmIUSFVKallmcioPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NDM3tTA2N3A0JkYNACKSPy4</recordid><startdate>20230915</startdate><enddate>20230915</enddate><creator>DONG SHUAI</creator><creator>YE RUNYUAN</creator><creator>ZOU KUN</creator><creator>FENG ZIJU</creator><creator>LI WENSHENG</creator><creator>XIONG KUNKUN</creator><scope>EVB</scope></search><sort><creationdate>20230915</creationdate><title>Training method of video behavior recognition model, and video behavior recognition method and device</title><author>DONG SHUAI ; YE RUNYUAN ; ZOU KUN ; FENG ZIJU ; LI WENSHENG ; XIONG KUNKUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116758370A3</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>DONG SHUAI</creatorcontrib><creatorcontrib>YE RUNYUAN</creatorcontrib><creatorcontrib>ZOU KUN</creatorcontrib><creatorcontrib>FENG ZIJU</creatorcontrib><creatorcontrib>LI WENSHENG</creatorcontrib><creatorcontrib>XIONG KUNKUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DONG SHUAI</au><au>YE RUNYUAN</au><au>ZOU KUN</au><au>FENG ZIJU</au><au>LI WENSHENG</au><au>XIONG KUNKUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Training method of video behavior recognition model, and video behavior recognition method and device</title><date>2023-09-15</date><risdate>2023</risdate><abstract>The invention provides a training method of a video behavior recognition model, and a video behavior recognition method and device. A specific embodiment of the method comprises the steps of inputting a sample image sequence corresponding to a sample video stream into an initial behavior recognition model; the sample video stream comprises a source domain sample video stream and a target domain sample video stream; the initial behavior recognition model comprises a classifier and a plurality of domain discriminators; aligning the features of the sample image sequence on different scales by using the plurality of domain discriminators to obtain a domain discrimination result; and training the initial behavior recognition model based on a classification result output by the classifier for the source domain sample video stream and domain discrimination results output by the plurality of domain discriminators. According to the method, the difference between the source domain sample video data and the target domai</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116758370A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Training method of video behavior recognition model, and video behavior 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=2025-01-29T02%3A50%3A08IST&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=DONG%20SHUAI&rft.date=2023-09-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116758370A%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