{"id":"https://openalex.org/W4415368601","doi":"https://doi.org/10.1109/tmm.2025.3618557","title":"MIP-CLIP: Multimodal Independent Prompt CLIP for Action Recognition","display_name":"MIP-CLIP: Multimodal Independent Prompt CLIP for Action Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415368601","doi":"https://doi.org/10.1109/tmm.2025.3618557"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3618557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618557","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/MIP-CLIP_Multimodal_Independent_Prompt_CLIP_for_Action_Recognition/28726685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiong Gao","orcid":"https://orcid.org/0000-0002-0899-6565"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Gao","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0899-6565","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000231514","display_name":"Zhaobin Chang","orcid":"https://orcid.org/0000-0002-1574-979X"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaobin Chang","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1574-979X","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039880090","display_name":"Dongyi Kong","orcid":"https://orcid.org/0000-0001-9407-1659"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyi Kong","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066119228","display_name":"Huiyu Zhou","orcid":"https://orcid.org/0000-0003-1634-9840"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiyu Zhou","raw_affiliation_strings":["School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1634-9840","affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082133960","display_name":"Yonggang Lu","orcid":"https://orcid.org/0000-0001-8926-2039"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonggang Lu","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8926-2039","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.25903069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"9918","last_page":"9930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9836000204086304,"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":0.9836000204086304,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9704999923706055,"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/generalizability-theory","display_name":"Generalizability theory","score":0.5972999930381775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4880000054836273},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48030000925064087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45989999175071716},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4336000084877014},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4047999978065491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629000186920166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6904000043869019},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.27810001373291016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3618557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3618557","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/28726685","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/MIP-CLIP_Multimodal_Independent_Prompt_CLIP_for_Action_Recognition/28726685","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/28726685","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/MIP-CLIP_Multimodal_Independent_Prompt_CLIP_for_Action_Recognition/28726685","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1578285471","https://openalex.org/W2100031962","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2157487986","https://openalex.org/W2507009361","https://openalex.org/W2520613337","https://openalex.org/W2770804203","https://openalex.org/W2962784628","https://openalex.org/W2963524571","https://openalex.org/W2970476646","https://openalex.org/W2999794487","https://openalex.org/W3009812836","https://openalex.org/W3012362498","https://openalex.org/W3035303837","https://openalex.org/W3126721948","https://openalex.org/W3157190320","https://openalex.org/W3159557112","https://openalex.org/W3174568846","https://openalex.org/W3175528717","https://openalex.org/W3182683290","https://openalex.org/W3198377975","https://openalex.org/W4205924026","https://openalex.org/W4210915468","https://openalex.org/W4214727094","https://openalex.org/W4214746887","https://openalex.org/W4280533444","https://openalex.org/W4281752744","https://openalex.org/W4296079457","https://openalex.org/W4297697565","https://openalex.org/W4312263092","https://openalex.org/W4312271977","https://openalex.org/W4312310776","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312769131","https://openalex.org/W4312956100","https://openalex.org/W4322731056","https://openalex.org/W4386065852","https://openalex.org/W4386071547","https://openalex.org/W4386072441","https://openalex.org/W4386076712","https://openalex.org/W4386973921","https://openalex.org/W4387010387","https://openalex.org/W4387587563","https://openalex.org/W4387969137","https://openalex.org/W4390872466","https://openalex.org/W4393148669","https://openalex.org/W4393153999","https://openalex.org/W4393158799","https://openalex.org/W4394896960","https://openalex.org/W4396767823"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"the":[1,14,28,33,75,87,105,113,119,127,136,143,154,163,187,191],"Contrastive":[2],"Language":[3],"Image":[4],"Pre-training":[5],"(CLIP)":[6],"model":[7,67],"has":[8],"shown":[9],"significant":[10,41],"generalizability":[11],"by":[12],"optimizing":[13],"distance":[15],"between":[16],"visual":[17,76,88,106,116,123,192],"and":[18,49,96,122,209],"text":[19,144,149],"features.":[20,117],"The":[21,197,211],"mainstream":[22],"CLIP-based":[23],"action":[24],"recognition":[25],"methods":[26],"mitigate":[27],"low":[29],"\u201czero-shot\u201d":[30,51],"generalization":[31],"of":[32,115,126,156,190],"1-of-N":[34,128],"paradigm":[35,129],"but":[36],"also":[37],"lead":[38],"to":[39,53,70,85,111,132,134,161,177],"a":[40,61,169],"degradation":[42],"in":[43],"supervised":[44,140,219],"performance.":[45,141],"Therefore,":[46],"powerful":[47],"supervision":[48],"competitive":[50,223],"need":[52,137],"be":[54],"effectively":[55],"traded":[56],"off.":[57],"In":[58],"this":[59,72],"work,":[60],"Multimodal":[62],"Independent":[63],"Prompt":[64,83],"CLIP":[65,133],"(MIP-CLIP)":[66],"is":[68,109,175],"proposed":[69,176],"address":[71],"challenge.":[73],"On":[74,142],"side,":[77,145],"we":[78,146],"propose":[79],"novel":[80],"Video":[81],"Motion":[82],"(VMP)":[84],"empower":[86],"encoder":[89],"with":[90],"motion":[91,98],"perception,":[92],"which":[93,185],"performs":[94],"short-":[95],"long-term":[97],"modelling":[99],"via":[100],"temporal":[101,120],"difference":[102,121],"operation.":[103],"Next,":[104],"classification":[107,124,193],"branch":[108,194],"introduced":[110],"improve":[112],"discrimination":[114],"Specifically,":[118],"operations":[125],"are":[130,199],"extended":[131],"satisfy":[135],"for":[138,181],"strong":[139],"design":[147],"Class-Agnostic":[148],"prompt":[150],"Template":[151],"(CAT)":[152],"under":[153],"constraint":[155],"Semantic":[157],"Alignment":[158],"(SA)":[159],"module":[160,174],"solve":[162],"label":[164],"semantic":[165],"dependency":[166],"problem.":[167],"Finally,":[168],"Dual-branch":[170],"Feature":[171],"Reconstruction":[172],"(DFR)":[173],"complete":[178],"cross-modal":[179],"interactions":[180],"better":[182],"feature":[183],"matching,":[184],"uses":[186],"class":[188],"confidence":[189],"as":[195],"input.":[196],"experiments":[198],"conducted":[200],"on":[201],"four":[202],"widely":[203],"used":[204],"benchmarks":[205],"(HMDB-51,":[206],"UCF-101,":[207],"Jester,":[208],"Kinetics-400).":[210],"results":[212],"demonstrate":[213],"that":[214],"our":[215],"method":[216],"achieves":[217],"excellent":[218],"performance":[220],"while":[221],"preserving":[222],"generalizability.":[224]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-21T00:00:00"}