{"id":"https://openalex.org/W4406171211","doi":"https://doi.org/10.1109/tcsvt.2025.3527312","title":"Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition","display_name":"Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition","publication_year":2025,"publication_date":"2025-01-08","ids":{"openalex":"https://openalex.org/W4406171211","doi":"https://doi.org/10.1109/tcsvt.2025.3527312"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3527312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3527312","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Yijun Pan","orcid":"https://orcid.org/0009-0007-4526-3858"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Pan","raw_affiliation_strings":["School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-4526-3858","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067555837","display_name":"Quan Zhao","orcid":"https://orcid.org/0000-0002-3897-3049"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Zhao","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3897-3049","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136560","display_name":"Yueyi Zhang","orcid":"https://orcid.org/0000-0003-0788-8826"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyi Zhang","raw_affiliation_strings":["National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0788-8826","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376572","display_name":"Zilei Wang","orcid":"https://orcid.org/0000-0003-1822-3731"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilei Wang","raw_affiliation_strings":["National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1822-3731","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656317","display_name":"Xiaoyan Sun","orcid":"https://orcid.org/0000-0003-3638-5566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Sun","raw_affiliation_strings":["National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3638-5566","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7266-5579","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.0827,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72570262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"35","issue":"6","first_page":"5912","last_page":"5924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9868999719619751,"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"}},{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7655699253082275},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6116710305213928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6109717488288879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46799275279045105},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44386619329452515},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08262869715690613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655699253082275},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6116710305213928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6109717488288879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46799275279045105},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44386619329452515},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08262869715690613},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3527312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3527312","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2064851185","https://openalex.org/W2108598243","https://openalex.org/W2507009361","https://openalex.org/W2625366777","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2894608918","https://openalex.org/W2895243423","https://openalex.org/W2951702519","https://openalex.org/W2957775769","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963783448","https://openalex.org/W2963811979","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996901793","https://openalex.org/W3034257141","https://openalex.org/W3035180180","https://openalex.org/W3035303837","https://openalex.org/W3035524453","https://openalex.org/W3035619757","https://openalex.org/W3114743660","https://openalex.org/W3126721948","https://openalex.org/W3162565403","https://openalex.org/W3175613352","https://openalex.org/W3184965686","https://openalex.org/W3190693140","https://openalex.org/W3191973200","https://openalex.org/W3196734898","https://openalex.org/W3203711169","https://openalex.org/W3206930349","https://openalex.org/W3216270236","https://openalex.org/W4206337866","https://openalex.org/W4214612132","https://openalex.org/W4214718285","https://openalex.org/W4221167396","https://openalex.org/W4281752744","https://openalex.org/W4296079410","https://openalex.org/W4309374824","https://openalex.org/W4312244159","https://openalex.org/W4312257792","https://openalex.org/W4312276384","https://openalex.org/W4312508659","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312839074","https://openalex.org/W4313886816","https://openalex.org/W4319300928","https://openalex.org/W4386065406","https://openalex.org/W4386072300","https://openalex.org/W4386076661","https://openalex.org/W4387969336","https://openalex.org/W4388871846","https://openalex.org/W4390871944","https://openalex.org/W4390872179","https://openalex.org/W4391759800","https://openalex.org/W4393160187","https://openalex.org/W4394593089","https://openalex.org/W4394618244","https://openalex.org/W4396903426","https://openalex.org/W4402754139","https://openalex.org/W4404724811","https://openalex.org/W4406046647","https://openalex.org/W6682864246","https://openalex.org/W6749916090","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6791353385","https://openalex.org/W6802919969","https://openalex.org/W6810334672","https://openalex.org/W6839415613","https://openalex.org/W6846726380","https://openalex.org/W6852826999","https://openalex.org/W6853201094","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Fine-grained":[0],"action":[1,40,155,166],"recognition":[2,41],"typically":[3],"faces":[4],"challenges":[5],"with":[6,56],"lower":[7],"inter-class":[8,32],"variances":[9],"and":[10,126,171,197],"higher":[11],"intra-class":[12,27],"variances.":[13],"Supervised":[14],"contrastive":[15,58,81,96,105,151],"learning":[16,82,97],"is":[17,102],"inherently":[18],"suitable":[19],"for":[20,94,153,164],"this":[21,74,135],"task,":[22],"as":[23,182],"it":[24,37],"can":[25],"decrease":[26],"feature":[28,190],"distances":[29,113],"while":[30],"increasing":[31],"ones.":[33],"However,":[34],"directly":[35],"applying":[36],"into":[38],"fine-grained":[39,115,154,165],"encounters":[42],"two":[43],"main":[44],"problems.":[45],"The":[46,99,173],"first":[47],"problem":[48,101],"stems":[49],"from":[50],"the":[51,78,88,95,111,130,139,146,149],"heavy":[52],"training":[53,63,91,204],"cost":[54],"associated":[55],"supervised":[57,80,104,150],"learning,":[59],"which":[60,85],"requires":[61],"numerous":[62],"epochs,":[64],"each":[65],"involving":[66],"double":[67],"augmentation":[68],"views":[69],"per":[70],"instance.":[71],"To":[72,133],"address":[73],"issue,":[75],"we":[76,137],"propose":[77],"late-stage":[79],"(late-SC)":[83],"strategy,":[84],"effectively":[86],"reduces":[87],"number":[89],"of":[90,148],"epochs":[92],"needed":[93],"process.":[98],"second":[100],"that":[103,176],"loss":[106,152],"does":[107],"not":[108],"explicitly":[109],"consider":[110],"semantic":[112],"between":[114],"actions":[116],"when":[117],"adjusting":[118],"representation":[119,131],"distances.":[120],"This":[121],"results":[122,174],"in":[123,203],"less":[124],"reasonable":[125],"efficient":[127],"adjustments":[128],"to":[129,181],"space.":[132],"overcome":[134],"limitation,":[136],"introduce":[138],"semantic-aware":[140],"temperature":[141],"adaptation":[142],"(STA)":[143],"mechanism,":[144],"enhancing":[145],"suitability":[147],"recognition.":[156],"We":[157],"conduct":[158],"experiments":[159],"on":[160],"several":[161],"benchmark":[162],"datasets":[163],"recognition,":[167],"including":[168],"Epic-Kitchens-55/100,":[169],"SomethingSomething-V1,":[170],"Diving48-V2.":[172],"demonstrate":[175],"our":[177],"proposed":[178],"method":[179],"(referred":[180],"LSC-STA)":[183],"consistently":[184],"enhances":[185],"performance":[186],"across":[187],"various":[188],"base":[189],"extractors,":[191],"without":[192],"introducing":[193],"additional":[194],"inference":[195],"overhead":[196],"incurring":[198],"only":[199],"a":[200],"marginal":[201],"increase":[202],"expenses.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}