{"id":"https://openalex.org/W4412888634","doi":"https://doi.org/10.18653/v1/2025.findings-acl.279","title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","display_name":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888634","doi":"https://doi.org/10.18653/v1/2025.findings-acl.279"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.279","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.279","pdf_url":"https://aclanthology.org/2025.findings-acl.279.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.279.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017703997","display_name":"Yeong-Joon Ju","orcid":"https://orcid.org/0009-0009-5552-2520"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yeong-Joon Ju","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001681270","display_name":"Ho\u2010Joong Kim","orcid":"https://orcid.org/0000-0002-8205-4648"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ho-Joong Kim","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057235109","display_name":"Seong-Whan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Korea University","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164862"],"apc_list":null,"apc_paid":null,"fwci":2.8558,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90761604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5350","last_page":"5363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9793999791145325,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9793999791145325,"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":0.9639999866485596,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9549000263214111,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7783647775650024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147575616836548},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6221811175346375},{"id":"https://openalex.org/keywords/mire","display_name":"Mire","score":0.5804205536842346},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5437750220298767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.535592794418335},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5005643367767334},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4999115467071533},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.4822295606136322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.447682648897171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35647332668304443},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.24862346053123474},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08607318997383118},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05827215313911438},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05511179566383362}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7783647775650024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147575616836548},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6221811175346375},{"id":"https://openalex.org/C2777634280","wikidata":"https://www.wikidata.org/wiki/Q36449705","display_name":"Mire","level":3,"score":0.5804205536842346},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5437750220298767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.535592794418335},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5005643367767334},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4999115467071533},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.4822295606136322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447682648897171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35647332668304443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24862346053123474},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08607318997383118},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05827215313911438},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05511179566383362},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C53657456","wikidata":"https://www.wikidata.org/wiki/Q184624","display_name":"Peat","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.279","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.279","pdf_url":"https://aclanthology.org/2025.findings-acl.279.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.279","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.279","pdf_url":"https://aclanthology.org/2025.findings-acl.279.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888634.pdf","grobid_xml":"https://content.openalex.org/works/W4412888634.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2968820833","https://openalex.org/W4380355808","https://openalex.org/W2068964259","https://openalex.org/W2013013717","https://openalex.org/W2558617677","https://openalex.org/W2342456189","https://openalex.org/W66256988","https://openalex.org/W4302857920","https://openalex.org/W4406273444","https://openalex.org/W1987340722"],"abstract_inverted_index":{"Recent":[0],"multimodal":[1,9,31,96,118,126],"retrieval":[2,57,98,127],"methods":[3,34],"have":[4],"endowed":[5],"text-based":[6],"retrievers":[7],"with":[8],"capabilities":[10],"by":[11,99],"utilizing":[12],"pre-training":[13,93,111],"strategies":[14],"for":[15,24,95],"visual-text":[16],"alignment.They":[17],"often":[18,35],"directly":[19],"fuse":[20],"the":[21,27,68,72,87,115,139,146],"two":[22],"modalities":[23],"cross-reference":[25],"during":[26,67],"alignment":[28],"to":[29,41,75,77],"understand":[30],"queries.However,":[32],"existing":[33],"overlook":[36],"crucial":[37],"visual":[38,78,88],"information":[39],"due":[40],"a":[42,56,92],"text-dominant":[43,147],"issue,":[44],"which":[45],"overly":[46],"depends":[47],"on":[48],"text-driven":[49,83],"signals.In":[50],"this":[51],"paper,":[52],"we":[53,90],"introduce":[54],"MIRe,":[55],"framework":[58,143],"that":[59,109],"achieves":[60],"modality":[61],"interaction":[62],"without":[63],"fusing":[64],"textual":[65,73],"features":[66],"alignment.Our":[69],"method":[70],"allows":[71],"query":[74,97],"attend":[76],"embeddings":[79],"while":[80],"not":[81],"feeding":[82],"signals":[84],"back":[85],"into":[86,104],"representations.Additionally,":[89],"construct":[91],"dataset":[94],"transforming":[100],"concise":[101],"question-answer":[102],"pairs":[103],"extended":[105],"passages.Our":[106],"experiments":[107],"demonstrate":[108],"our":[110,132,142],"strategy":[112],"significantly":[113],"enhances":[114],"understanding":[116],"of":[117,141],"queries,":[119],"resulting":[120],"in":[121,144],"strong":[122],"performance":[123],"across":[124],"four":[125],"benchmarks":[128],"under":[129],"zero-shot":[130],"settings.Moreover,":[131],"ablation":[133],"studies":[134],"and":[135],"analyses":[136],"explicitly":[137],"verify":[138],"effectiveness":[140],"mitigating":[145],"issue.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}
