{"id":"https://openalex.org/W4403913144","doi":"https://doi.org/10.1145/3678957.3685725","title":"Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?","display_name":"Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403913144","doi":"https://doi.org/10.1145/3678957.3685725"},"language":"en","primary_location":{"id":"doi:10.1145/3678957.3685725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","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/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-2053-9068","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010891850","display_name":"Daniel Yang","orcid":"https://orcid.org/0000-0002-7684-9057"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Yang","raw_affiliation_strings":["Signal Analysis and Interpretation Lab, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-7684-9057","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059652479","display_name":"Digbalay Bose","orcid":"https://orcid.org/0000-0002-5281-1695"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Digbalay Bose","raw_affiliation_strings":["Signal Analysis and Interpretation Lab, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-5281-1695","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Lab, University of Southern California, United States"],"raw_orcid":"https://orcid.org/0000-0002-1052-6204","affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Lab, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22573856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"133"},"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":0.9983999729156494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8128697872161865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.75350421667099},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6426571607589722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251002550125122},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4438869059085846},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4333745837211609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3623700737953186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3437207043170929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34207987785339355}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8128697872161865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75350421667099},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6426571607589722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251002550125122},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4438869059085846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4333745837211609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3623700737953186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3437207043170929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34207987785339355},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678957.3685725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2296448531","https://openalex.org/W2741295496","https://openalex.org/W2744999500","https://openalex.org/W2798683079","https://openalex.org/W2962711930","https://openalex.org/W2963573392","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W3080565611","https://openalex.org/W3135367836","https://openalex.org/W3154596443","https://openalex.org/W3156892778","https://openalex.org/W3175825020","https://openalex.org/W3184735396","https://openalex.org/W3205786327","https://openalex.org/W3206201541","https://openalex.org/W4225303565","https://openalex.org/W4281633595","https://openalex.org/W4290877962","https://openalex.org/W4290944617","https://openalex.org/W4306820534","https://openalex.org/W4313164293","https://openalex.org/W4376226279","https://openalex.org/W4385801086","https://openalex.org/W4386071707","https://openalex.org/W4386071994","https://openalex.org/W4386072096","https://openalex.org/W4394597798","https://openalex.org/W6790978476"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W627697492"],"abstract_inverted_index":{"Multi-modal":[0],"learning":[1,24,51,82],"has":[2],"emerged":[3],"as":[4],"an":[5],"increasingly":[6],"promising":[7],"avenue":[8],"in":[9,49],"vision":[10],"recognition,":[11],"driving":[12],"innovations":[13],"across":[14],"diverse":[15,119],"domains.":[16],"Despite":[17],"its":[18],"success,":[19],"the":[20,32,40,63,87,99],"robustness":[21,92,144],"of":[22,34,37,65,118],"multi-modal":[23,50,70,81,107],"for":[25],"visual":[26,41,95,110,123,137,146],"recognition":[27,111],"is":[28,158],"often":[29],"challenged":[30],"by":[31,97],"unavailability":[33],"a":[35,77,115],"subset":[36],"modalities,":[38],"especially":[39],"modality.":[42],"Conventional":[43],"approaches":[44],"to":[45,68,85],"mitigate":[46],"missing":[47,94,100,122,136,148],"modalities":[48],"rely":[52],"heavily":[53],"on":[54],"modality":[55,96],"fusion":[56],"schemes.":[57],"In":[58],"contrast,":[59],"this":[60],"paper":[61],"explores":[62],"use":[64],"text-to-image":[66],"models":[67],"assist":[69],"learning.":[71],"Specifically,":[72],"we":[73,113,155],"propose":[74],"and":[75,90,141,152,164,171],"explore":[76],"simple":[78,165],"but":[79],"effective":[80,159],"framework":[83],"GTI-MM":[84,157],"enhance":[86],"data":[88,101,133,138,147],"efficiency":[89,134],"model":[91,143],"against":[93],"imputing":[98],"with":[102,109,135,145,160],"generative":[103],"models.":[104],"Using":[105],"multiple":[106],"datasets":[108],"tasks,":[112],"present":[114],"comprehensive":[116],"analysis":[117],"conditions":[120],"involving":[121],"data.":[124],"Our":[125,168],"findings":[126],"show":[127],"that":[128],"synthetic":[129,172],"images":[130,173],"benefit":[131],"training":[132,140,151],"during":[139,149],"improve":[142],"both":[150],"testing.":[153],"Moreover,":[154],"demonstrate":[156],"lower":[161],"generation":[162],"quantity":[163],"prompt":[166],"techniques.":[167],"code":[169],"base":[170],"are":[174],"at":[175],"https://github.com/usc-sail/GTI-MM.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}