Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement
The invention discloses a multi-modal middle school experiment step detection method and system based on motion target semantic enhancement, and the method comprises the steps: firstly carrying out the preprocessing of a video frame, obtaining a motion region through frame difference, obtaining a mo...
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 YI XING WULUE GU YANHUI YUAN HAOMIAO ZHOU JUNSHENG |
| description | The invention discloses a multi-modal middle school experiment step detection method and system based on motion target semantic enhancement, and the method comprises the steps: firstly carrying out the preprocessing of a video frame, obtaining a motion region through frame difference, obtaining a motion target through a target detection technology, and extracting a semantic time sequence feature through a BERT model; and performing time sequence dependence modeling on the video features in an encoder to obtain step-level visual time sequence features, fusing the step-level visual time sequence features with moving target semantic features in a decoder, constructing a relation between experiment steps and corresponding targets, and realizing accurate detection of the experiment steps in a middle school experiment video. The method can more effectively capture unique motion characteristics of the experimental steps, effectively distinguish different steps, realize accurate judgment of the experimental steps, an |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118411652A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118411652A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118411652A3</originalsourceid><addsrcrecordid>eNqNjDsOwjAQBdNQIOAOywFShJ9oUQSigYo-WuxHYslem3hBcHuCxAGopph5b1zcTw-vrgzRsqfgrPWgbLoYPeGV0LsAUcqKRBYKoy4KBWgXLbFYyu_BBbpyhqWvik8nLSn3LYYdAos6Q5COxeB7Ni1GN_YZsx8nxfywv9THEik2yIkNBNrU56rarqpqs17slv80H-PaRDA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement</title><source>esp@cenet</source><creator>CHEN YI ; XING WULUE ; GU YANHUI ; YUAN HAOMIAO ; ZHOU JUNSHENG</creator><creatorcontrib>CHEN YI ; XING WULUE ; GU YANHUI ; YUAN HAOMIAO ; ZHOU JUNSHENG</creatorcontrib><description>The invention discloses a multi-modal middle school experiment step detection method and system based on motion target semantic enhancement, and the method comprises the steps: firstly carrying out the preprocessing of a video frame, obtaining a motion region through frame difference, obtaining a motion target through a target detection technology, and extracting a semantic time sequence feature through a BERT model; and performing time sequence dependence modeling on the video features in an encoder to obtain step-level visual time sequence features, fusing the step-level visual time sequence features with moving target semantic features in a decoder, constructing a relation between experiment steps and corresponding targets, and realizing accurate detection of the experiment steps in a middle school experiment video. The method can more effectively capture unique motion characteristics of the experimental steps, effectively distinguish different steps, realize accurate judgment of the experimental steps, an</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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=20240730&DB=EPODOC&CC=CN&NR=118411652A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240730&DB=EPODOC&CC=CN&NR=118411652A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN YI</creatorcontrib><creatorcontrib>XING WULUE</creatorcontrib><creatorcontrib>GU YANHUI</creatorcontrib><creatorcontrib>YUAN HAOMIAO</creatorcontrib><creatorcontrib>ZHOU JUNSHENG</creatorcontrib><title>Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement</title><description>The invention discloses a multi-modal middle school experiment step detection method and system based on motion target semantic enhancement, and the method comprises the steps: firstly carrying out the preprocessing of a video frame, obtaining a motion region through frame difference, obtaining a motion target through a target detection technology, and extracting a semantic time sequence feature through a BERT model; and performing time sequence dependence modeling on the video features in an encoder to obtain step-level visual time sequence features, fusing the step-level visual time sequence features with moving target semantic features in a decoder, constructing a relation between experiment steps and corresponding targets, and realizing accurate detection of the experiment steps in a middle school experiment video. The method can more effectively capture unique motion characteristics of the experimental steps, effectively distinguish different steps, realize accurate judgment of the experimental steps, an</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDsOwjAQBdNQIOAOywFShJ9oUQSigYo-WuxHYslem3hBcHuCxAGopph5b1zcTw-vrgzRsqfgrPWgbLoYPeGV0LsAUcqKRBYKoy4KBWgXLbFYyu_BBbpyhqWvik8nLSn3LYYdAos6Q5COxeB7Ni1GN_YZsx8nxfywv9THEik2yIkNBNrU56rarqpqs17slv80H-PaRDA</recordid><startdate>20240730</startdate><enddate>20240730</enddate><creator>CHEN YI</creator><creator>XING WULUE</creator><creator>GU YANHUI</creator><creator>YUAN HAOMIAO</creator><creator>ZHOU JUNSHENG</creator><scope>EVB</scope></search><sort><creationdate>20240730</creationdate><title>Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement</title><author>CHEN YI ; XING WULUE ; GU YANHUI ; YUAN HAOMIAO ; ZHOU JUNSHENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118411652A3</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN YI</creatorcontrib><creatorcontrib>XING WULUE</creatorcontrib><creatorcontrib>GU YANHUI</creatorcontrib><creatorcontrib>YUAN HAOMIAO</creatorcontrib><creatorcontrib>ZHOU JUNSHENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN YI</au><au>XING WULUE</au><au>GU YANHUI</au><au>YUAN HAOMIAO</au><au>ZHOU JUNSHENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement</title><date>2024-07-30</date><risdate>2024</risdate><abstract>The invention discloses a multi-modal middle school experiment step detection method and system based on motion target semantic enhancement, and the method comprises the steps: firstly carrying out the preprocessing of a video frame, obtaining a motion region through frame difference, obtaining a motion target through a target detection technology, and extracting a semantic time sequence feature through a BERT model; and performing time sequence dependence modeling on the video features in an encoder to obtain step-level visual time sequence features, fusing the step-level visual time sequence features with moving target semantic features in a decoder, constructing a relation between experiment steps and corresponding targets, and realizing accurate detection of the experiment steps in a middle school experiment video. The method can more effectively capture unique motion characteristics of the experimental steps, effectively distinguish different steps, realize accurate judgment of the experimental steps, an</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118411652A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Multi-modal middle school experiment step detection method and system based on moving target semantic enhancement |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T08%3A55%3A59IST&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%20YI&rft.date=2024-07-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118411652A%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 |