{"id":"https://openalex.org/W4415344121","doi":"https://doi.org/10.1109/iccv51701.2025.02088","title":"Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations","display_name":"Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415344121","doi":"https://doi.org/10.1109/iccv51701.2025.02088"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.03304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101994555","display_name":"Hai Huang","orcid":"https://orcid.org/0000-0001-8745-8142"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367775","display_name":"Yan Xia","orcid":"https://orcid.org/0000-0002-4539-298X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xia","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060861535","display_name":"S. Zhou","orcid":"https://orcid.org/0000-0002-7517-9653"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sashuai Zhou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072365834","display_name":"Hanting Wang","orcid":"https://orcid.org/0000-0003-2761-577X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanting Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078789660","display_name":"Shulei Wang","orcid":"https://orcid.org/0000-0001-7440-9544"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulei Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15010942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22488","last_page":"22498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.958299994468689,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.958299994468689,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9060999751091003,"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/generalization","display_name":"Generalization","score":0.7505000233650208},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.57669997215271},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5084999799728394},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4284999966621399},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.423799991607666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41620001196861267},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7505000233650208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050000190734863},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.57669997215271},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.299699991941452},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2628999948501587}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.02088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.03304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03304","pdf_url":"https://arxiv.org/pdf/2507.03304","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:2507.03304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03304","pdf_url":"https://arxiv.org/pdf/2507.03304","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/G6072681302","display_name":null,"funder_award_id":"62222211","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Domain":[0,61],"Generalization":[1,62],"(DG)":[2],"aims":[3],"to":[4,72,74,84,96,110,118,126,138,163,173],"enhance":[5],"model":[6],"robustness":[7],"in":[8,59,129,146,221],"unseen":[9,75],"or":[10],"distributionally":[11],"shifted":[12],"target":[13,76,114],"domains":[14,115],"through":[15],"training":[16],"exclusively":[17],"on":[18,69,206],"source":[19],"domains.":[20],"Although":[21],"existing":[22],"DG":[23,95,171],"techniques,":[24],"such":[25],"as":[26],"data":[27],"manipulation,":[28],"learning":[29],"strategies,":[30],"and":[31,50,116,194,211,216],"representation":[32],"learning,":[33],"have":[34],"shown":[35],"significant":[36],"progress,":[37],"they":[38],"predominantly":[39],"address":[40,151],"single-modal":[41,94],"data.":[42],"With":[43],"the":[44,79,85,111,130,181,199,214],"emergence":[45],"of":[46,113,201,218],"numerous":[47],"multi-modal":[48,54,70,178,223],"datasets":[49],"increasing":[51],"demand":[52],"for":[53],"tasks,":[55],"a":[56,156,187],"key":[57],"challenge":[58],"Multi-modal":[60],"(MMDG)":[63],"has":[64],"emerged:":[65],"enabling":[66,176],"models":[67],"trained":[68],"sources":[71],"generalize":[73],"distributions":[77],"within":[78,180],"same":[80],"modality":[81,128],"set.":[82],"Due":[83],"inherent":[86],"differences":[87],"between":[88],"modalities,":[89,144],"directly":[90],"transferring":[91],"methods":[92,103,124,172],"from":[93],"MMDG":[97,131,174],"typically":[98],"yields":[99],"sub-optimal":[100],"results.":[101],"These":[102],"often":[104],"exhibit":[105],"randomness":[106],"during":[107],"generalization":[108,140,148],"due":[109],"invisibility":[112],"fail":[117],"consider":[119],"inter-modal":[120],"consistency.":[121],"Applying":[122],"these":[123,152],"independently":[125],"each":[127],"setting":[132],"before":[133],"combining":[134],"them":[135],"can":[136],"lead":[137],"divergent":[139],"directions":[141],"across":[142],"different":[143,165],"resulting":[145],"degraded":[147],"capabilities.":[149],"To":[150],"challenges,":[153],"we":[154,185],"propose":[155],"novel":[157],"approach":[158],"that":[159,191],"leverages":[160],"Unified":[161],"Representations":[162],"map":[164],"paired":[166],"modalities":[167],"together,":[168],"effectively":[169],"adapting":[170],"by":[175],"synchronized":[177],"improvements":[179],"unified":[182,202],"space.":[183],"Additionally,":[184],"introduce":[186],"supervised":[188],"disentanglement":[189],"framework":[190],"separates":[192],"modal-general":[193],"modal-specific":[195],"information,":[196],"further":[197],"enhancing":[198,222],"alignment":[200],"representations.":[203],"Extensive":[204],"experiments":[205],"benchmark":[207],"datasets,":[208],"including":[209],"EPIC-Kitchens":[210],"Human-Animal-Cartoon,":[212],"demonstrate":[213],"effectiveness":[215],"superiority":[217],"our":[219],"method":[220],"domain":[224],"generalization.":[225]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-20T00:00:00"}