{"id":"https://openalex.org/W4408166104","doi":"https://doi.org/10.1109/lsp.2025.3548448","title":"From Body Parts to Holistic Action: A Fine-Grained Teacher-Student CLIP for Action Recognition","display_name":"From Body Parts to Holistic Action: A Fine-Grained Teacher-Student CLIP for Action Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408166104","doi":"https://doi.org/10.1109/lsp.2025.3548448"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3548448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3548448","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":"https://openalex.org/A5047420153","display_name":"Yangjun Ou","orcid":"https://orcid.org/0000-0002-4142-4833"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangjun Ou","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4142-4833","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102086552","display_name":"Xiao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Shi","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086814847","display_name":"Jia Chen","orcid":"https://orcid.org/0000-0002-6350-6610"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076582919","display_name":"Ruhan He","orcid":"https://orcid.org/0000-0002-1918-6939"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruhan He","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-1918-6939","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chi Liu","orcid":"https://orcid.org/0000-0003-4670-7450"},"institutions":[{"id":"https://openalex.org/I2250865144","display_name":"TCL (China)","ror":"https://ror.org/04dzjva98","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250865144"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Liu","raw_affiliation_strings":["TCL Corporate Research, Wuhan, China","TCL Research, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4670-7450","affiliations":[{"raw_affiliation_string":"TCL Corporate Research, Wuhan, China","institution_ids":["https://openalex.org/I2250865144"]},{"raw_affiliation_string":"TCL Research, Wuhan, China","institution_ids":["https://openalex.org/I2250865144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047420153"],"corresponding_institution_ids":["https://openalex.org/I4210119942"],"apc_list":null,"apc_paid":null,"fwci":1.2845,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76064183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1336","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9742000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6691062450408936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6189787983894348},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5159955024719238},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34515810012817383},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3397054672241211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32168054580688477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18622207641601562},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.13699227571487427},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08804595470428467}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6691062450408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189787983894348},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5159955024719238},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34515810012817383},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3397054672241211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32168054580688477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18622207641601562},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.13699227571487427},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08804595470428467},{"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/lsp.2025.3548448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3548448","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3509117036","display_name":null,"funder_award_id":"2023HBITF05","funder_id":"https://openalex.org/F4320327462","funder_display_name":"Wuhan Textile University"},{"id":"https://openalex.org/G5483097416","display_name":null,"funder_award_id":"62202345","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/F4320327462","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2117141700","https://openalex.org/W2126579184","https://openalex.org/W2805029945","https://openalex.org/W2917819557","https://openalex.org/W2982936646","https://openalex.org/W2996906606","https://openalex.org/W3198377975","https://openalex.org/W3214346043","https://openalex.org/W4210773761","https://openalex.org/W4282981352","https://openalex.org/W4285154053","https://openalex.org/W4304014690","https://openalex.org/W4312310776","https://openalex.org/W4360770727","https://openalex.org/W4386065554","https://openalex.org/W4386065852","https://openalex.org/W4386071547","https://openalex.org/W4387587791","https://openalex.org/W4387951823","https://openalex.org/W4388854793","https://openalex.org/W4389722224","https://openalex.org/W4390120146","https://openalex.org/W4392903964","https://openalex.org/W4395447302","https://openalex.org/W4396214363","https://openalex.org/W4402753597","https://openalex.org/W4402783842","https://openalex.org/W6600983433","https://openalex.org/W6765307894","https://openalex.org/W6791353385","https://openalex.org/W6861592674"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2084487854","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Action":[0],"recognition":[1,49],"in":[2],"dynamic":[3],"video":[4],"remains":[5],"challenging,":[6],"particularly":[7],"when":[8],"distinguishing":[9],"between":[10,57],"visually":[11],"similar":[12],"actions.":[13],"While":[14],"existing":[15],"methods":[16],"often":[17],"rely":[18],"on":[19,130,137],"holistic":[20,47],"representations,":[21],"they":[22],"overlook":[23],"the":[24,55,86,95,146],"fine-grained":[25,58],"details":[26],"that":[27,41],"are":[28,80],"significant":[29],"for":[30],"accurate":[31],"classification.":[32],"We":[33],"propose":[34],"a":[35,51,111,133,142],"novel":[36],"Fine-grained":[37],"Teacher-student":[38],"CLIP":[39],"(FT-CLIP)":[40],"integrates":[42],"body":[43,70,122],"part":[44,123],"analysis":[45,124],"with":[46,92],"action":[48,59,63,103,127],"through":[50],"teacher-student":[52],"architecture,":[53],"bridging":[54],"gap":[56],"parsing":[60],"and":[61,83,136,139],"overall":[62],"understanding.":[64],"The":[65],"teacher":[66],"model":[67,97],"processes":[68],"individual":[69],"parts":[71],"alongside":[72],"specialized":[73],"description":[74],"to":[75,100,125],"generate":[76],"part-specific":[77],"features,":[78],"which":[79],"then":[81],"aggregated":[82],"distilled":[84],"into":[85],"student":[87,96],"model.":[88],"Through":[89],"knowledge":[90],"distillation":[91],"learnable":[93],"prompts,":[94],"effectively":[98],"learns":[99],"capture":[101],"subtle":[102],"distinctions":[104],"while":[105],"maintaining":[106],"efficient":[107],"inference.":[108],"FT-CLIP":[109],"achieves":[110],"more":[112],"nuanced":[113],"understanding":[114],"of":[115,148],"complex":[116],"actions":[117],"by":[118],"progressing":[119],"from":[120],"detailed":[121],"comprehensive":[126],"recognition.":[128],"Experiments":[129],"Kinetics-TPS":[131],"under":[132,141],"fully-supervised":[134],"setting":[135,144],"HMDB51":[138],"UCF101":[140],"zero-shot":[143],"demonstrate":[145],"effectiveness":[147],"our":[149],"method.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}