{"id":"https://openalex.org/W4411687687","doi":"https://doi.org/10.1109/tii.2025.3577686","title":"TransCLIP: Transferring Vision\u2013Language Models for Efficient Video Action Recognition","display_name":"TransCLIP: Transferring Vision\u2013Language Models for Efficient Video Action Recognition","publication_year":2025,"publication_date":"2025-06-26","ids":{"openalex":"https://openalex.org/W4411687687","doi":"https://doi.org/10.1109/tii.2025.3577686"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2025.3577686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3577686","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5101642780","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-3737-3201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Tianmushan Laboratory, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3737-3201","affiliations":[{"raw_affiliation_string":"Tianmushan Laboratory, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036020328","display_name":"Yanzhou Su","orcid":"https://orcid.org/0000-0002-3377-469X"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhou Su","raw_affiliation_strings":["Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3377-469X","affiliations":[{"raw_affiliation_string":"Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason Gu","orcid":"https://orcid.org/0000-0002-7626-1077"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Electrical and Computer Engineering, Dalhousie University, Halifax, NS, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7626-1077","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88692515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"21","issue":"10","first_page":"7643","last_page":"7652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9930999875068665,"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":0.9729999899864197,"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/computer-science","display_name":"Computer science","score":0.718742847442627},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.622156023979187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.570771336555481},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5453252196311951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5268279910087585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34732627868652344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718742847442627},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.622156023979187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.570771336555481},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5453252196311951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5268279910087585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34732627868652344},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2025.3577686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3577686","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6376497011","display_name":null,"funder_award_id":"2022TQ0315","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2625366777","https://openalex.org/W2883429621","https://openalex.org/W2963155035","https://openalex.org/W3081434152","https://openalex.org/W3126721948","https://openalex.org/W3198377975","https://openalex.org/W4304014690","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312651322","https://openalex.org/W4362593875","https://openalex.org/W4382467086","https://openalex.org/W4385245566","https://openalex.org/W4386065554","https://openalex.org/W4386071547","https://openalex.org/W4386072441","https://openalex.org/W4387969137","https://openalex.org/W4388854793","https://openalex.org/W4402727584"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Transferring":[0],"contrastive":[1,7,167],"vision-language":[2],"pretrained":[3],"models,":[4],"such":[5],"as":[6],"language\u2013image":[8],"pretraining":[9],"(CLIP),":[10],"to":[11,68,122,156,172],"video":[12,176,201],"recognition":[13,203],"task":[14],"has":[15],"attracted":[16],"much":[17],"attention.":[18],"Recent":[19],"studies":[20],"in":[21,133,161],"this":[22,59],"area":[23],"utilized":[24],"prompt":[25,77,90],"learning":[26,48,182],"within":[27],"either":[28],"text":[29,84,101,178],"or":[30,33],"vision":[31,82,99],"branches,":[32,102,179],"employed":[34,171],"an":[35],"end-to-end":[36],"CLIP":[37],"fine-tuning":[38],"approach.":[39],"However,":[40],"these":[41],"methods":[42,198],"do":[43],"not":[44],"fully":[45],"leverage":[46,130],"the":[47,81,108,114,119,175,181,185],"potential":[49],"of":[50,98,113,184],"two":[51],"branches":[52],"and":[53,76,83,100,103,110,152,177],"may":[54],"compromise":[55],"zero-shot":[56],"generalization.":[57],"In":[58,163],"work,":[60],"we":[61,87,135],"present":[62],"a":[63,137,165],"multimodal":[64],"framework":[65],"TransCLIP,":[66],"aiming":[67],"adapt":[69],"vision\u2013language":[70],"models":[71],"by":[72],"integrating":[73],"both":[74],"adapter":[75],"tuning":[78],"techniques":[79],"for":[80],"encoders.":[85],"Specifically,":[86],"incorporate":[88],"learnable":[89],"tokens":[91],"into":[92,107],"each":[93],"transformer":[94],"encoder":[95],"layer\u2019s":[96],"input":[97],"integrate":[104],"lightweight":[105],"adapters":[106],"key":[109],"value":[111],"matrices":[112],"multi-head":[115],"self-attention":[116],"modules,":[117],"enhancing":[118,180],"model\u2019s":[120],"capability":[121,183],"capture":[123],"more":[124],"related":[125],"video-specific":[126],"features.":[127],"To":[128],"effectively":[129],"temporal":[131,138,159],"information":[132],"videos,":[134],"implement":[136],"difference":[139],"attention":[140,155],"module":[141],"(TemDiff":[142],"attn)":[143],"that":[144],"explicitly":[145],"computes":[146],"differences":[147],"between":[148],"adjacent":[149],"frame":[150],"embeddings":[151],"conducts":[153],"difference-level":[154],"encode":[157],"motion-related":[158],"dependency":[160],"videos.":[162],"addition,":[164],"coarse-and-fine":[166],"leaning":[168],"strategy":[169],"is":[170],"better":[173],"align":[174],"whole":[186],"framework.":[187],"Across":[188],"different":[189],"evaluation":[190],"settings,":[191],"our":[192],"model":[193],"consistently":[194],"outperforms":[195],"previous":[196],"State-of-the-Art":[197],"on":[199],"several":[200],"action":[202],"benchmarks.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}