{"id":"https://openalex.org/W4415540681","doi":"https://doi.org/10.1145/3746027.3755288","title":"Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning","display_name":"Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540681","doi":"https://doi.org/10.1145/3746027.3755288"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5111154303","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0009-0005-5689-3818"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-5689-3818","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Yu","orcid":"https://orcid.org/0009-0009-6097-4556"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Yu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-6097-4556","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397623","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5245-3584"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5245-3584","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037595310","display_name":"Jianfeng Lu","orcid":"https://orcid.org/0000-0002-9190-507X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Lu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9190-507X","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8106","last_page":"8115"},"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9941999912261963,"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/modalities","display_name":"Modalities","score":0.7038000226020813},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6079000234603882},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6047000288963318},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5978000164031982},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5759000182151794},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5501000285148621},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.44369998574256897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5673999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5586000084877014},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5501000285148621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.44369998574256897},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3198377975","https://openalex.org/W4382318032","https://openalex.org/W4382318126"],"related_works":[],"abstract_inverted_index":{"The":[0,167],"integration":[1],"of":[2],"prompt":[3,72,92],"tuning":[4],"with":[5],"multimodal":[6],"learning":[7,101,110],"has":[8],"shown":[9],"significant":[10],"generalization":[11],"abilities":[12],"for":[13,36,56,85],"various":[14,157],"downstream":[15],"tasks.":[16],"Despite":[17],"advancements,":[18],"existing":[19],"methods":[20],"heavily":[21],"depend":[22],"on":[23,153],"massive":[24],"modality-specific":[25,146],"labeled":[26,147],"data":[27],"(e.g.,":[28],"video,":[29],"audio,":[30],"and":[31,76,94,108,131,164],"image),":[32],"or":[33],"are":[34],"customized":[35],"a":[37,53,58],"single":[38],"modality.":[39],"In":[40],"this":[41],"study,":[42],"we":[43],"present":[44],"Text":[45],"as":[46],"Any-Modality":[47],"by":[48,89],"Consistent":[49],"Prompt":[50],"Tuning":[51],"(TaAM-CPT),":[52],"scalable":[54,129],"approach":[55],"constructing":[57],"general":[59],"representation":[60],"model":[61],"toward":[62],"unlimited":[63,141],"modalities":[64,88,118],"using":[65],"solely":[66],"text":[67,74,78,96],"data.":[68],"TaAM-CPT":[69,105,134,149],"comprises":[70],"modality":[71],"pools,":[73],"construction,":[75],"modality-aligned":[77,95],"encoders":[79],"from":[80,127],"pre-trained":[81,132],"models,":[82,133],"which":[83,112],"allows":[84],"extending":[86],"new":[87],"simply":[90],"adding":[91],"pools":[93],"encoders.":[97],"To":[98],"harmonize":[99],"the":[100],"across":[102,123],"different":[103,124],"modalities,":[104,158],"designs":[106],"intra-":[107],"inter-modal":[109],"objectives,":[111],"can":[113,135],"capture":[114],"category":[115],"details":[116],"within":[117],"while":[119],"maintaining":[120],"semantic":[121],"consistency":[122],"modalities.":[125,142],"Benefiting":[126],"its":[128],"architecture":[130],"be":[136],"seamlessly":[137],"extended":[138],"to":[139],"accommodate":[140],"Remarkably,":[143],"without":[144],"any":[145],"data,":[148],"achieves":[150],"leading":[151],"results":[152],"diverse":[154],"datasets":[155],"spanning":[156],"including":[159],"video":[160],"classification,":[161,163],"image":[162],"audio":[165],"classification.":[166],"code":[168],"is":[169],"available":[170],"at":[171],"https://github.com/Jinx630/TaAM-CPT.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}