{"id":"https://openalex.org/W4388854793","doi":"https://doi.org/10.1109/tnnls.2023.3331841","title":"ActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition","display_name":"ActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388854793","doi":"https://doi.org/10.1109/tnnls.2023.3331841","pmid":"https://pubmed.ncbi.nlm.nih.gov/37988204"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3331841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3331841","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","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/A5100429685","display_name":"Mengmeng Wang","orcid":"https://orcid.org/0000-0003-4035-0630"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengmeng Wang","raw_affiliation_strings":["Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4035-0630","affiliations":[{"raw_affiliation_string":"Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083788268","display_name":"Jiazheng Xing","orcid":"https://orcid.org/0000-0001-7280-249X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazheng Xing","raw_affiliation_strings":["Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074067442","display_name":"Jianbiao Mei","orcid":"https://orcid.org/0000-0003-3849-2736"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbiao Mei","raw_affiliation_strings":["Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3849-2736","affiliations":[{"raw_affiliation_string":"Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Laboratory of Advanced Perception on Robotics and Intelligent Learning, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Control Science and Engineering, Laboratory of Advanced Perception on Robotics and Intelligent Learning, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066982002","display_name":"Yunliang Jiang","orcid":"https://orcid.org/0000-0003-4500-5836"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunliang Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"],"raw_orcid":"https://orcid.org/0000-0003-4500-5836","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China","institution_ids":["https://openalex.org/I135237710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100429685"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":9.3422,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98697727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"625","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944999814033508,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9667999744415283,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8314313888549805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6080152988433838},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5958196520805359},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5057249069213867},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4897441864013672},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46274641156196594},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.44875040650367737},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4418397545814514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.428621768951416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4170101583003998},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33529409766197205},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.14960619807243347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314313888549805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6080152988433838},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5958196520805359},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5057249069213867},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4897441864013672},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46274641156196594},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.44875040650367737},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4418397545814514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.428621768951416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4170101583003998},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33529409766197205},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.14960619807243347},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3331841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3331841","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37988204","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37988204","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1682403713","https://openalex.org/W1983364832","https://openalex.org/W2024868105","https://openalex.org/W2068611653","https://openalex.org/W2126579184","https://openalex.org/W2337252826","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2736596806","https://openalex.org/W2746726611","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2809562466","https://openalex.org/W2883429621","https://openalex.org/W2955874753","https://openalex.org/W2962843773","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963457877","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963722382","https://openalex.org/W2963820951","https://openalex.org/W2981385151","https://openalex.org/W2984008963","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996901793","https://openalex.org/W3013853001","https://openalex.org/W3034572008","https://openalex.org/W3034600407","https://openalex.org/W3035303837","https://openalex.org/W3035413240","https://openalex.org/W3035619757","https://openalex.org/W3126721948","https://openalex.org/W3159557112","https://openalex.org/W3168640669","https://openalex.org/W3175528717","https://openalex.org/W3180353325","https://openalex.org/W3185341429","https://openalex.org/W3193810785","https://openalex.org/W3198377975","https://openalex.org/W3205021045","https://openalex.org/W3210279979","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4225683910","https://openalex.org/W4284898017","https://openalex.org/W4285606530","https://openalex.org/W4286212078","https://openalex.org/W4297697565","https://openalex.org/W4306831165","https://openalex.org/W4312407537","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312614039","https://openalex.org/W4312769131","https://openalex.org/W4312810944","https://openalex.org/W4312818263","https://openalex.org/W4312971576","https://openalex.org/W4385245566","https://openalex.org/W4386065554","https://openalex.org/W4386072441","https://openalex.org/W4387587563","https://openalex.org/W6682864246","https://openalex.org/W6750041603","https://openalex.org/W6766904570","https://openalex.org/W6777648310","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6797265648","https://openalex.org/W6797737728","https://openalex.org/W6798805250","https://openalex.org/W6803872405","https://openalex.org/W6811387395","https://openalex.org/W6838865580","https://openalex.org/W6846313647","https://openalex.org/W6849878650"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2062195135","https://openalex.org/W2912415823","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"The":[0],"canonical":[1],"approach":[2],"to":[3,12,25,56,99,113,173,190],"video":[4,88],"action":[5,51,102,139,170,221],"recognition":[6,52,103,171,222],"dictates":[7],"a":[8,14,27,47,76,81,129,157,216,231],"neural":[9],"network":[10],"model":[11,72,98],"do":[13,100],"classic":[15],"and":[16,95,120,146,208],"standard":[17],"1-of-N":[18],"majority":[19],"vote":[20],"task.":[21],"They":[22],"are":[23],"trained":[24],"predict":[26],"fixed":[28],"set":[29],"of":[30,60,117,123,160,198],"predefined":[31],"categories,":[32],"limiting":[33],"their":[34],"transferability":[35],"on":[36,50,133,156,187,219,228],"new":[37,48,130,200],"datasets":[38,189],"with":[39,90,230],"unseen":[40],"concepts.":[41],"In":[42],"this":[43,73,134],"article,":[44],"we":[45,71,127,142],"provide":[46],"perspective":[49],"by":[53],"attaching":[54],"importance":[55],"the":[57,87,115,169,199,234],"semantic":[58,92],"information":[59],"label":[61,118],"texts":[62,119],"rather":[63],"than":[64],"simply":[65],"mapping":[66],"them":[67],"into":[68],"numbers.":[69],"Specifically,":[70],"task":[74,172],"as":[75,233],"video-text":[77,164],"matching":[78],"problem":[79],"within":[80],"multimodal":[82,135],"learning":[83,136],"framework,":[84],"which":[85,141,203],"strengthens":[86],"representation":[89],"more":[91,175],"language":[93],"supervision":[94],"enables":[96],"our":[97],"zero-shot":[101],"without":[104],"any":[105],"further":[106],"labeled":[107],"data":[108],"or":[109,163],"parameters'":[110],"requirements.":[111],"Moreover,":[112],"handle":[114],"deficiency":[116],"make":[121],"use":[122],"tremendous":[124],"web":[125,161],"data,":[126],"propose":[128],"paradigm":[131,149],"based":[132],"framework":[137],"for":[138],"recognition,":[140],"dub":[143],"\"pre-train,":[144],"adapt":[145],"fine-tune.\"":[147],"This":[148],"first":[150],"learns":[151],"powerful":[152],"representations":[153],"from":[154],"pre-training":[155,177],"large":[158],"amount":[159],"image-text":[162],"data.":[165],"Then,":[166],"it":[167,183],"makes":[168],"act":[174],"like":[176],"problems":[178],"via":[179],"adaptation":[180],"engineering.":[181],"Finally,":[182],"is":[184,237],"fine-tuned":[185],"end-to-end":[186],"target":[188],"obtain":[191],"strong":[192],"performance.":[193],"We":[194],"give":[195],"an":[196],"instantiation":[197],"paradigm,":[201],"ActionCLIP,":[202],"not":[204],"only":[205],"has":[206],"superior":[207],"flexible":[209],"zero-shot/few-shot":[210],"transfer":[211],"ability":[212],"but":[213],"also":[214],"reaches":[215],"top":[217],"performance":[218],"general":[220],"task,":[223],"achieving":[224],"83.8%":[225],"top-1":[226],"accuracy":[227],"Kinetics-400":[229],"ViT-B/16":[232],"backbone.":[235],"Code":[236],"available":[238],"at":[239],"https://github.com/sallymmx/ActionCLIP.git.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":57},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}