{"id":"https://openalex.org/W4392426151","doi":"https://doi.org/10.1109/tcsvt.2024.3424566","title":"Multi-Modal Attribute Prompting for Vision-Language Models","display_name":"Multi-Modal Attribute Prompting for Vision-Language Models","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4392426151","doi":"https://doi.org/10.1109/tcsvt.2024.3424566"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3424566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3424566","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.00219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114860063","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-3791-3984"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3791-3984","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiamin Wu","orcid":"https://orcid.org/0000-0003-4380-5573"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Wu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4380-5573","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenfei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Yang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049974020","display_name":"Xu Zhou","orcid":"https://orcid.org/0000-0002-5094-032X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Technologies Inc., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc., Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1559,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95053834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"11","first_page":"11579","last_page":"11591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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/T10028","display_name":"Topic Modeling","score":0.9613999724388123,"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/modal","display_name":"Modal","score":0.687570333480835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5664368867874146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42086178064346313},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4101920425891876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37456345558166504},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11410155892372131}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.687570333480835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5664368867874146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42086178064346313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4101920425891876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37456345558166504},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11410155892372131},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3424566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3424566","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.00219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00219","pdf_url":"https://arxiv.org/pdf/2403.00219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.00219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00219","pdf_url":"https://arxiv.org/pdf/2403.00219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1691810814","display_name":null,"funder_award_id":"62306294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4406814025","display_name":null,"funder_award_id":"JCKY2020903B002","funder_id":"https://openalex.org/F4320335833","funder_display_name":"National Defense Basic Scientific Research Program of China"},{"id":"https://openalex.org/G4952126428","display_name":null,"funder_award_id":"2023M743385","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8390538724","display_name":null,"funder_award_id":"2308085QF222","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335833","display_name":"National Defense Basic Scientific Research Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2032699694","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2126448884","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2170881581","https://openalex.org/W2533598788","https://openalex.org/W2596142952","https://openalex.org/W2789209438","https://openalex.org/W2948968650","https://openalex.org/W2964194231","https://openalex.org/W2981165461","https://openalex.org/W3027585699","https://openalex.org/W3037492894","https://openalex.org/W3044438666","https://openalex.org/W3106542916","https://openalex.org/W3107094551","https://openalex.org/W3169422999","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W3198571508","https://openalex.org/W3209086464","https://openalex.org/W3213454282","https://openalex.org/W4205991051","https://openalex.org/W4207055979","https://openalex.org/W4229453513","https://openalex.org/W4233762729","https://openalex.org/W4289792608","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312910992","https://openalex.org/W4313175608","https://openalex.org/W4318764497","https://openalex.org/W4321021726","https://openalex.org/W4323338501","https://openalex.org/W4360892253","https://openalex.org/W4379382677","https://openalex.org/W4386065742","https://openalex.org/W4386071547","https://openalex.org/W4386138397","https://openalex.org/W4386187806","https://openalex.org/W4386699374","https://openalex.org/W4386790226","https://openalex.org/W4390190253","https://openalex.org/W4390872306","https://openalex.org/W4390872773","https://openalex.org/W4390874497","https://openalex.org/W4392223601","https://openalex.org/W4394951233","https://openalex.org/W4395027807","https://openalex.org/W6638677478","https://openalex.org/W6678800043","https://openalex.org/W6682962330","https://openalex.org/W6755207826","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6776700526","https://openalex.org/W6778883912","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6800217721","https://openalex.org/W6803872405","https://openalex.org/W6849976536","https://openalex.org/W6853690301","https://openalex.org/W6854061876","https://openalex.org/W6854250507","https://openalex.org/W6856800273","https://openalex.org/W6856935247","https://openalex.org/W6857256894"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-trained":[0],"Vision-Language":[1],"Models":[2],"(VLMs),":[3],"like":[4],"CLIP,":[5],"exhibit":[6],"strong":[7],"generalization":[8,48],"ability":[9,39,49],"to":[10,40,50,99,125,143],"downstream":[11],"tasks":[12],"but":[13],"struggle":[14],"in":[15],"few-shot":[16,150],"scenarios.":[17],"Existing":[18],"prompting":[19],"techniques":[20],"primarily":[21],"focus":[22],"on":[23,155],"global":[24,123],"text":[25],"and":[26,45,78],"image":[27],"representations,":[28],"yet":[29],"overlooking":[30],"multi-modal":[31],"attribute":[32,73,76,92,97],"characteristics.":[33],"This":[34],"limitation":[35],"hinders":[36],"the":[37,117,122,127,140],"model\u2019s":[38],"perceive":[41],"fine-grained":[42,110],"visual":[43,75,91,102,111],"details":[44],"restricts":[46],"its":[47],"a":[51,63],"broader":[52],"range":[53],"of":[54,129],"unseen":[55],"classes.":[56],"To":[57,135],"address":[58],"this":[59,138],"issue,":[60],"we":[61,88],"propose":[62],"Multi-modal":[64],"Attribute":[65],"Prompting":[66],"method":[67,161],"(MAP)":[68],"by":[69,95],"jointly":[70],"exploring":[71],"textual":[72,96],"prompting,":[74,77],"attribute-level":[79,119,146],"alignment.":[80],"The":[81],"proposed":[82,118],"MAP":[83],"enjoys":[84],"several":[85],"merits.":[86],"First,":[87],"introduce":[89],"learnable":[90],"prompts":[93],"enhanced":[94],"semantics":[98],"adaptively":[100],"capture":[101],"attributes":[103],"for":[104,114,132,148],"images":[105],"from":[106],"unknown":[107],"categories,":[108],"boosting":[109],"perception":[112],"capabilities":[113],"CLIP.":[115],"Second,":[116],"alignment":[120,124,131,147],"complements":[121],"enhance":[126],"robustness":[128],"cross-modal":[130,145],"open-vocabulary":[133],"objects.":[134],"our":[136,160],"knowledge,":[137],"is":[139],"first":[141],"work":[142],"establish":[144],"CLIP-based":[149],"adaptation.":[151],"Extensive":[152],"experimental":[153],"results":[154],"11":[156],"datasets":[157],"demonstrate":[158],"that":[159],"performs":[162],"favorably":[163],"against":[164],"state-of-the-art":[165],"approaches.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
