{"id":"https://openalex.org/W4415708987","doi":"https://doi.org/10.1109/icme59968.2025.11209870","title":"The Motion in the Details: Adapting CLIP for Action Recognition via Dual-prompt Guidance","display_name":"The Motion in the Details: Adapting CLIP for Action Recognition via Dual-prompt Guidance","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708987","doi":"https://doi.org/10.1109/icme59968.2025.11209870"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5034649165","display_name":"Longjuan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longjuan Sun","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067613982","display_name":"Xixia Xu","orcid":"https://orcid.org/0000-0001-6305-475X"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixia Xu","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078385469","display_name":"Dongchen Zhu","orcid":"https://orcid.org/0000-0002-1579-3942"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchen Zhu","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamao Li","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27302076,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8652999997138977,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8652999997138977,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0674000009894371,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.025100000202655792,"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/discriminative-model","display_name":"Discriminative model","score":0.7138000130653381},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6398000121116638},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6392999887466431},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5238000154495239},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.492000013589859},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127999901771545},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7138000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6520000100135803},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5238000154495239},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4011000096797943},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2768999934196472}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2904378456","https://openalex.org/W2981385151","https://openalex.org/W3126721948","https://openalex.org/W3177934633","https://openalex.org/W4214612132","https://openalex.org/W4214746887","https://openalex.org/W4312480274","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4312938727","https://openalex.org/W4386065554","https://openalex.org/W4386065852","https://openalex.org/W4386072365","https://openalex.org/W4390872452","https://openalex.org/W4390872466","https://openalex.org/W4402716475","https://openalex.org/W4402754229","https://openalex.org/W4402979950","https://openalex.org/W4402980592","https://openalex.org/W4403780727"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"large-scale":[1],"pre-trained":[2,34],"language-image":[3],"models":[4,19],"like":[5],"CLIP":[6],"have":[7],"shown":[8],"extraordinary":[9],"capabilities":[10],"for":[11],"understanding":[12],"image-level":[13],"objects,":[14],"but":[15],"naively":[16],"transferring":[17],"such":[18],"to":[20,41,50,64,79,109,126,167],"video":[21,136],"recognition":[22],"is":[23,56],"still":[24],"unsatisfactory.":[25],"Existing":[26],"methods":[27],"design":[28],"plugged":[29],"temporal":[30,86,117,153],"modules":[31],"into":[32],"the":[33,38,43,51,59,81,111,116,135,139,146,156,161],"model":[35],"or":[36,55],"explore":[37],"vision-text":[39],"relation":[40],"improve":[42],"performance,":[44],"which":[45],"either":[46],"demonstrated":[47],"insufficient":[48],"attention":[49],"frame-wise":[52],"action":[53,103,157],"subject":[54,104,158],"limited":[57],"by":[58],"unreliable":[60],"prompt":[61,96,105],"guidance,":[62],"struggling":[63],"achieve":[65],"better":[66],"adaptation.":[67],"In":[68],"this":[69],"work,":[70],"we":[71],"present":[72],"DP-CLIP,":[73],"a":[74],"novel":[75],"dual-prompt":[76],"guidance":[77,97],"mechanism":[78],"disentangle":[80],"adaptation":[82],"in":[83,152],"textual":[84],"and":[85,100,114,129,143,159,175,186],"aspects.":[87],"Specifically,":[88],"DP-CLIP":[89],"consists":[90],"of":[91],"an":[92,101,123],"explicit":[93],"instruction-filtered":[94,124],"caption":[95],"(ECPG)":[98],"module":[99,108],"implicit":[102],"mining":[106],"(ISPM)":[107],"maximize":[110],"textual-visual":[112],"alignment":[113],"enhance":[115],"reasoning":[118],"ability.":[119],"The":[120],"former":[121],"designs":[122],"strategy":[125],"generate":[127],"reliable":[128],"reasonable":[130],"semantic":[131],"captions":[132],"matching":[133],"with":[134],"details,":[137],"narrowing":[138],"gap":[140],"between":[141],"videos":[142],"labels.":[144],"Further,":[145],"ISPM":[147],"emphasizes":[148],"action-related":[149],"discriminative":[150],"clues":[151],"via":[154],"highlighting":[155],"refining":[160],"motion":[162],"cues":[163],"across":[164,184],"frames,":[165],"immune":[166],"irrelevant":[168],"interference.":[169],"Extensive":[170],"experiments":[171],"on":[172],"Kinetics-400,":[173],"HMDB-51":[174],"UCF-101":[176],"demonstrate":[177],"that":[178],"our":[179],"method":[180],"achieves":[181],"state-of-the-art":[182],"performance":[183],"fully-supervised":[185],"zero-shot":[187],"settings.":[188]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}
