{"id":"https://openalex.org/W4382999123","doi":"https://doi.org/10.1109/tmm.2023.3291588","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","display_name":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","publication_year":2023,"publication_date":"2023-07-03","ids":{"openalex":"https://openalex.org/W4382999123","doi":"https://doi.org/10.1109/tmm.2023.3291588"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3291588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3291588","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089584286","display_name":"Yinghui Xing","orcid":"https://orcid.org/0000-0001-6021-8261"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Xing","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Research Development Institute, Northwestern Polytechnical University in Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6021-8261","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Research Development Institute, Northwestern Polytechnical University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988632","display_name":"Qirui Wu","orcid":"https://orcid.org/0000-0002-1587-7062"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirui Wu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067159497","display_name":"De Cheng","orcid":"https://orcid.org/0000-0003-4603-847X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Cheng","raw_affiliation_strings":["School of Telecommunications Engineering, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-4603-847X","affiliations":[{"raw_affiliation_string":"School of Telecommunications Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033395835","display_name":"Shizhou Zhang","orcid":"https://orcid.org/0000-0003-3429-576X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhou Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3429-576X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025755839","display_name":"Guoqiang Liang","orcid":"https://orcid.org/0000-0002-8710-5520"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Liang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-8710-5520","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396097","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-9218-9132"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9218-9132","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-2977-8057","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.1888,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98327572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"2056","last_page":"2068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8914104700088501},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6213394403457642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5852571725845337},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48889389634132385},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.45871832966804504},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45416906476020813},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4370476305484772},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43213266134262085},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4252403974533081},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4184945225715637},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4176669120788574},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41549280285835266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3409200608730316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12293201684951782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8914104700088501},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6213394403457642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5852571725845337},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48889389634132385},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45871832966804504},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45416906476020813},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4370476305484772},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43213266134262085},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4252403974533081},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4184945225715637},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4176669120788574},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41549280285835266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3409200608730316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12293201684951782},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3291588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3291588","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1584941972","display_name":null,"funder_award_id":"62201467","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4479186740","display_name":null,"funder_award_id":"62101453","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7740149046","display_name":null,"funder_award_id":"2022TQ0260","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G796754823","display_name":null,"funder_award_id":"2021A1515110544","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G844604588","display_name":null,"funder_award_id":"62176198","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W24089286","https://openalex.org/W1846799578","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2566349545","https://openalex.org/W2964194231","https://openalex.org/W2965572487","https://openalex.org/W3024314529","https://openalex.org/W3034827765","https://openalex.org/W3035524453","https://openalex.org/W3037492894","https://openalex.org/W3041700978","https://openalex.org/W3044438666","https://openalex.org/W3090449556","https://openalex.org/W3098267758","https://openalex.org/W3115894062","https://openalex.org/W3177096435","https://openalex.org/W3182683290","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3204250462","https://openalex.org/W4205277845","https://openalex.org/W4205536765","https://openalex.org/W4205991051","https://openalex.org/W4226058394","https://openalex.org/W4226313640","https://openalex.org/W4226416422","https://openalex.org/W4229453513","https://openalex.org/W4281838252","https://openalex.org/W4283838088","https://openalex.org/W4290058072","https://openalex.org/W4304098539","https://openalex.org/W4307106676","https://openalex.org/W4312238419","https://openalex.org/W4312310776","https://openalex.org/W4312430871","https://openalex.org/W4312614039","https://openalex.org/W4312651322","https://openalex.org/W4312655527","https://openalex.org/W4312818263","https://openalex.org/W4313156423","https://openalex.org/W4313175608","https://openalex.org/W4313186260","https://openalex.org/W4313477435","https://openalex.org/W4386790226","https://openalex.org/W4390873714","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6738045163","https://openalex.org/W6739901393","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6779326418","https://openalex.org/W6784185929","https://openalex.org/W6784333009","https://openalex.org/W6785440099","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802347785","https://openalex.org/W6803567076","https://openalex.org/W6803728867","https://openalex.org/W6838789006","https://openalex.org/W6838865580","https://openalex.org/W6840657638"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2384605597","https://openalex.org/W2988126442","https://openalex.org/W2387743295","https://openalex.org/W4388335561","https://openalex.org/W2187606256","https://openalex.org/W2275988210"],"abstract_inverted_index":{"With":[0],"the":[1,36,41,62,67,74,78,83,115,122,142,151,166,181,187],"emergence":[2],"of":[3,20,55,82,186],"large":[4],"pretrained":[5,42],"vison-language":[6],"models":[7],"such":[8],"as":[9,58],"CLIP,":[10],"transferable":[11],"representations":[12],"can":[13,71],"be":[14,87],"adapted":[15],"to":[16,91,163],"a":[17,53,99,126],"wide":[18],"range":[19],"downstream":[21,33,167],"tasks":[22,34],"via":[23],"prompt":[24,69,102,129,145,156],"tuning.":[25],"Prompt":[26],"tuning":[27,66,103,130],"probes":[28],"for":[29,32],"beneficial":[30],"information":[31,169],"from":[35,61],"general":[37],"knowledge":[38],"stored":[39],"in":[40,136],"model.":[43],"A":[44],"recently":[45],"proposed":[46,135,188],"method":[47],"named":[48],"Context":[49],"Optimization":[50],"(CoOp)":[51],"introduces":[52],"set":[54],"learnable":[56],"vectors":[57],"text":[59,68,108,155],"prompts":[60,111],"language":[63],"side.":[64],"However,":[65],"alone":[70],"only":[72],"adjust":[73],"synthesized":[75],"\u201cclassifier\u201d,":[76],"while":[77],"computed":[79],"visual":[80,110,124,128,144,171],"features":[81,157],"image":[84,117,159],"encoder":[85],"cannot":[86],"affected,":[88],"thus":[89],"leading":[90],"suboptimal":[92],"solutions.":[93],"In":[94,139],"this":[95,140],"article,":[96],"we":[97],"propose":[98],"novel":[100],"dual-modality":[101],"(DPT)":[104],"paradigm":[105],"through":[106],"learning":[107],"and":[109,158,170,183],"simultaneously.":[112],"To":[113],"make":[114],"final":[116],"feature":[118],"concentrate":[119],"more":[120],"on":[121,177],"target":[123],"concept,":[125],"class-aware":[127,143],"(CAVPT)":[131],"scheme":[132],"is":[133,146],"further":[134],"our":[137],"DPT.":[138],"scheme,":[141],"generated":[147],"dynamically":[148],"by":[149],"performing":[150],"cross":[152],"attention":[153],"between":[154],"patch":[160],"token":[161],"embeddings":[162],"encode":[164],"both":[165],"task-related":[168],"instance":[172],"information.":[173],"Extensive":[174],"experimental":[175],"results":[176],"11":[178],"datasets":[179],"demonstrate":[180],"effectiveness":[182],"generalization":[184],"ability":[185],"method.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}