{"id":"https://openalex.org/W7154690718","doi":"https://doi.org/10.1109/tip.2026.3683256","title":"Vision\u2013Language Collaborative Representation Learning for Action Quality Assessment","display_name":"Vision\u2013Language Collaborative Representation Learning for Action Quality Assessment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154690718","doi":"https://doi.org/10.1109/tip.2026.3683256","pmid":"https://pubmed.ncbi.nlm.nih.gov/41996432"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3683256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3683256","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026792871","display_name":"Kumie Gedamu","orcid":"https://orcid.org/0000-0002-6458-1882"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Kumie Gedamu","raw_affiliation_strings":["Department of Computer Science, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-6458-1882","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9122-6141","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology., Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology., Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020978568","display_name":"Jamal Bentahar","orcid":"https://orcid.org/0000-0002-3136-4849"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Jamal Bentahar","raw_affiliation_strings":["Department of Computer Science and the 6G Research Center, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-3136-4849","affiliations":[{"raw_affiliation_string":"Department of Computer Science and the 6G Research Center, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133915639","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2615-1555","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43581751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4686","last_page":"4700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38940000534057617,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38940000534057617,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.28870001435279846,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04699999839067459,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5473999977111816},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4189000129699707},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41280001401901245},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.39579999446868896},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.37040001153945923},{"id":"https://openalex.org/keywords/action-learning","display_name":"Action learning","score":0.3562999963760376},{"id":"https://openalex.org/keywords/online-assessment","display_name":"Online assessment","score":0.30869999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5473999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077999830245972},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41280001401901245},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.3562999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C178823583","wikidata":"https://www.wikidata.org/wiki/Q3269883","display_name":"Online assessment","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C554579003","wikidata":"https://www.wikidata.org/wiki/Q474157","display_name":"Collaborative software","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3683256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3683256","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41996432","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41996432","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G281939877","display_name":null,"funder_award_id":"2024JDHJ0059","funder_id":"https://openalex.org/F4320333335","funder_display_name":"Sichuan Province Science and Technology Support Program"},{"id":"https://openalex.org/G5480161566","display_name":null,"funder_award_id":"W2433164","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320333335","display_name":"Sichuan Province Science and Technology Support Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Action":[0],"Quality":[1],"Assessment":[2],"(AQA)":[3],"has":[4],"gained":[5],"significant":[6],"attention":[7],"due":[8,55],"to":[9,26,50,56,78,107,130,156],"its":[10],"potential":[11],"real-world":[12],"applications,":[13],"which":[14,186],"require":[15],"a":[16,60,71,85,102],"fine-grained":[17,80,120],"understanding":[18],"of":[19,183],"action":[20,81,117,121,133,138,167],"sequences.":[21],"Recent":[22],"works":[23],"have":[24],"attempted":[25],"utilize":[27],"multimodal":[28,153],"video":[29],"features":[30,134],"and":[31,52,83,115,159,177],"address":[32],"some":[33],"existing":[34],"challenges.":[35],"However,":[36],"these":[37,67,148],"approaches":[38],"primarily":[39],"focus":[40],"on":[41,172],"leveraging":[42],"textual":[43,163],"information":[44],"from":[45],"language":[46],"models":[47],"only,":[48],"leading":[49],"instability":[51],"suboptimal":[53],"performance":[54],"directional":[57],"bias":[58],"in":[59],"vision-language":[61,112,127],"joint":[62,145],"embedding":[63],"space.":[64],"To":[65],"tackle":[66],"issues,":[68],"we":[69,100,125,151],"propose":[70,152],"Vision-Language":[72],"Collaboration":[73],"Representation":[74],"Learning":[75],"approach":[76],"(VLC-Net)":[77],"understand":[79],"sequences":[82],"create":[84],"unified":[86],"feature":[87,122],"representation":[88],"along":[89],"with":[90,135,162],"their":[91,144],"temporal":[92],"dependencies":[93],"for":[94,119],"accurate":[95,166],"AQA":[96],"score":[97],"prediction.":[98],"Specifically,":[99],"design":[101,126],"bidirectional":[103],"knowledge":[104,114,118],"distillation":[105],"operation":[106],"perform":[108],"collaboration":[109],"learning":[110,155],"between":[111],"pre-trained":[113],"visual":[116],"learning.":[123],"Furthermore,":[124],"alignment":[128],"guidance":[129],"explicitly":[131],"align":[132,160],"the":[136,173,181],"same":[137],"semantics":[139],"across":[140],"modalities,":[141],"thereby":[142],"unifying":[143],"representation.":[146,168],"Leveraging":[147],"aligned":[149],"features,":[150],"contrastive":[154],"relate":[157],"modalities":[158],"subactions":[161],"descriptions,":[164],"ensuring":[165],"We":[169],"conduct":[170],"experiments":[171],"FineDiving,":[174],"MTL-AQA,":[175],"FineFS,":[176],"Fis-V":[178],"datasets,":[179],"demonstrating":[180],"effectiveness":[182],"our":[184],"approach,":[185],"outperforms":[187],"state-of-the-art":[188],"methods.":[189]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-04-18T00:00:00"}
