{"id":"https://openalex.org/W4415708141","doi":"https://doi.org/10.1109/icme59968.2025.11209533","title":"Decoupling Representations with Quantized Vectors for Semi-Supervised Action Quality Assessment","display_name":"Decoupling Representations with Quantized Vectors for Semi-Supervised Action Quality Assessment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708141","doi":"https://doi.org/10.1109/icme59968.2025.11209533"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5025033657","display_name":"Lingfeng Ye","orcid":"https://orcid.org/0009-0009-7350-6938"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lingfeng Ye","raw_affiliation_strings":["Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026792871","display_name":"Kumie Gedamu","orcid":"https://orcid.org/0000-0002-6458-1882"},"institutions":[{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kumie Gedamu","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Yibin,Yibin,China"],"affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin,Yibin,China","institution_ids":["https://openalex.org/I4210131342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China,Shenzhen,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025033657"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84693432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9117000102996826,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9117000102996826,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.00839999970048666,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7246000170707703},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6413999795913696},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5916000008583069},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5396000146865845},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4941999912261963},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.40779998898506165}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948000192642212},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4945000112056732},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666000008583069},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4023999869823456},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2260521078","https://openalex.org/W2552035314","https://openalex.org/W2604806576","https://openalex.org/W2796214461","https://openalex.org/W2939039198","https://openalex.org/W2953867939","https://openalex.org/W2963524571","https://openalex.org/W2964159205","https://openalex.org/W2990759760","https://openalex.org/W2995113766","https://openalex.org/W3035714233","https://openalex.org/W3093182158","https://openalex.org/W3118508703","https://openalex.org/W3193654597","https://openalex.org/W3207409354","https://openalex.org/W4205745489","https://openalex.org/W4224088546","https://openalex.org/W4312243874","https://openalex.org/W4312419390","https://openalex.org/W4312560592","https://openalex.org/W4312785375","https://openalex.org/W4381299118","https://openalex.org/W4385245566","https://openalex.org/W4386071938","https://openalex.org/W4387968012","https://openalex.org/W4403182097"],"related_works":[],"abstract_inverted_index":{"Semi-supervised":[0],"Action":[1],"Quality":[2],"Assessment":[3],"(AQA)":[4],"aims":[5],"to":[6,38,65],"predict":[7],"action":[8,31,62],"execution":[9,63],"scores":[10],"by":[11,125],"utilizing":[12],"limited":[13],"labeled":[14,89],"and":[15,29,61,80,90,109,120,138],"massive":[16],"unlabeled":[17,45,91,118],"samples.":[18],"However,":[19],"existing":[20],"approaches":[21],"often":[22],"oversimplify":[23],"the":[24,105,122,142],"modeling":[25],"process":[26],"of":[27,70],"scene-invariant":[28],"fine-grained":[30,68],"sequences":[32],"for":[33,72,117],"score":[34,101],"prediction,":[35],"which":[36,57],"fails":[37],"fully":[39],"leverage":[40],"rich":[41],"information":[42],"available":[43,152],"in":[44],"data.":[46],"Thus,":[47],"we":[48,111],"propose":[49],"a":[50,67,94],"Vector":[51],"Quantized":[52],"Decoupling":[53],"representation":[54],"Network":[55],"(VQD-Net),":[56],"decouples":[58],"sub-action":[59],"categories":[60],"quality":[64],"enable":[66],"understanding":[69],"actions":[71],"semi-supervised":[73],"AQA.":[74],"The":[75,148],"proposed":[76,143],"VQD-Net":[77,144],"effectively":[78],"captures":[79],"learns":[81],"discriminative":[82],"features":[83,108],"through":[84],"common":[85],"semantic":[86],"representations":[87],"between":[88,107],"samples":[92,119],"within":[93],"shared":[95],"embedding":[96],"space,":[97],"enabling":[98],"accurate":[99,114],"AQA":[100,133],"prediction.":[102],"By":[103],"leveraging":[104],"differences":[106],"embeddings,":[110],"achieve":[112],"more":[113],"confidence":[115],"estimates":[116],"enhance":[121],"model":[123],"performance":[124],"selecting":[126],"reliable":[127],"pseudo-labels.":[128],"Experiments":[129],"on":[130],"three":[131],"public":[132],"datasets,":[134],"including":[135],"MTL-AQA,":[136],"RG,":[137],"FineFS,":[139],"demonstrate":[140],"that":[141],"achieves":[145],"state-of-the-art":[146],"performance.":[147],"source":[149],"code":[150],"is":[151],"at":[153],"https://github.com/Pix0611/VQD-Net.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}