{"id":"https://openalex.org/W4417073199","doi":"https://doi.org/10.1145/3743093.3770978","title":"CPR-CLIP: Cross-modal Consistent and Prompt-diverse Regularized CLIP for Action Recognition","display_name":"CPR-CLIP: Cross-modal Consistent and Prompt-diverse Regularized CLIP for Action Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073199","doi":"https://doi.org/10.1145/3743093.3770978"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022425701","display_name":"Hao Song","orcid":"https://orcid.org/0009-0006-3497-0381"},"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":"Hao Song","raw_affiliation_strings":["the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"],"raw_orcid":"https://orcid.org/0009-0006-3497-0381","affiliations":[{"raw_affiliation_string":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yangjun Ou","raw_affiliation_strings":["the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4142-4833","affiliations":[{"raw_affiliation_string":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092354266","display_name":"Chen Wang","orcid":"https://orcid.org/0009-0009-2375-3332"},"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":"Chen Wang","raw_affiliation_strings":["the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-2375-3332","affiliations":[{"raw_affiliation_string":"the School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, wuhan, China","institution_ids":["https://openalex.org/I4210119942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119942"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44917263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5389000177383423,"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":0.5389000177383423,"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":0.20900000631809235,"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"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.07259999960660934,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/action","display_name":"Action (physics)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35339999198913574},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.3328999876976013},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.304500013589859},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2786000072956085}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5218999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47749999165534973},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3328999876976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3190999925136566},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G112339833","display_name":null,"funder_award_id":"2023AFB294","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"}],"funders":[{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2126579184","https://openalex.org/W2507009361","https://openalex.org/W2625366777","https://openalex.org/W2963524571","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3138516171","https://openalex.org/W3198377975","https://openalex.org/W4312310776","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312614039","https://openalex.org/W4386065554","https://openalex.org/W4386071547","https://openalex.org/W4387031409","https://openalex.org/W4388854793","https://openalex.org/W4390872773","https://openalex.org/W4390873112","https://openalex.org/W4393149172","https://openalex.org/W4401857415","https://openalex.org/W4405867679","https://openalex.org/W4406821790","https://openalex.org/W4413146108","https://openalex.org/W4413147126"],"related_works":[],"abstract_inverted_index":{"Prompt":[0,114],"learning":[1,79],"has":[2,22],"emerged":[3],"as":[4,17],"an":[5],"effective":[6],"strategy":[7,90],"for":[8],"adapting":[9],"multimodal":[10],"vision-language":[11],"models":[12],"to":[13,41,91,119,152],"downstream":[14],"tasks":[15],"such":[16],"video":[18,29],"action":[19,81],"recognition,":[20],"which":[21],"been":[23],"widely":[24],"applied":[25],"in":[26,80],"human-computer":[27],"interaction,":[28],"surveillance":[30],"and":[31,44,65,128,135,139],"medical":[32],"fields.":[33],"However,":[34],"existing":[35,147],"approaches":[36],"often":[37],"suffer":[38],"from":[39],"overfitting":[40,105],"task-specific":[42],"distributions":[43],"prompt":[45,78,108,126],"collapse,":[46],"especially":[47],"under":[48,137],"limited":[49],"data":[50],"or":[51],"when":[52],"class":[53],"semantics":[54],"are":[55],"highly":[56],"similar.":[57],"In":[58],"this":[59],"work,":[60],"we":[61,84,111],"propose":[62],"Cross-modal":[63,86],"Consistent":[64],"Prompt-diverse":[66],"Regularized":[67],"CLIP":[68,101],"(CPR-CLIP),":[69],"a":[70,113],"flexible":[71],"framework":[72],"that":[73,143],"enhances":[74],"the":[75,93,99],"generalization":[76,151],"of":[77],"recognition.":[82],"Specifically,":[83],"introduce":[85],"Consistency":[87],"Regularization":[88,116],"(CCR)":[89],"preserve":[92],"original":[94],"feature":[95],"representations":[96],"encoded":[97],"by":[98,107],"frozen":[100],"encoder,":[102],"thereby":[103],"reducing":[104],"caused":[106],"adaptation.":[109],"Additionally,":[110],"design":[112],"Diversity":[115],"(PDR)":[117],"term":[118],"encourage":[120],"category-wise":[121],"separation":[122],"among":[123],"prompts,":[124],"alleviating":[125],"collapse":[127],"enhancing":[129],"discriminability.":[130],"Experiments":[131],"on":[132],"HMDB51,":[133],"UCF101,":[134],"SSv2":[136],"base-to-novel":[138],"few-shot":[140],"settings":[141],"show":[142],"CPR-CLIP":[144],"consistently":[145],"outperforms":[146],"methods,":[148],"achieving":[149],"strong":[150],"novel":[153],"classes.":[154]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-12-06T00:00:00"}