{"id":"https://openalex.org/W4416033916","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1211","title":"BRIT: Bidirectional Retrieval over Unified Image-Text Graph","display_name":"BRIT: Bidirectional Retrieval over Unified Image-Text Graph","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033916","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1211"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1211","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1211.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: EMNLP 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-emnlp.1211.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039867061","display_name":"Ainulla Khan","orcid":"https://orcid.org/0009-0007-4062-2049"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]},{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Ainulla Khan","raw_affiliation_strings":["Fujitsu Research of India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India","institution_ids":["https://openalex.org/I2252096349","https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006390702","display_name":"Moyuru Yamada","orcid":"https://orcid.org/0009-0009-1907-7503"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]},{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Moyuru Yamada","raw_affiliation_strings":["Fujitsu Research of India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India","institution_ids":["https://openalex.org/I2252096349","https://openalex.org/I4210159607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072125669","display_name":"Srinidhi Akella","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]},{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Srinidhi Akella","raw_affiliation_strings":["Fujitsu Research of India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India","institution_ids":["https://openalex.org/I2252096349","https://openalex.org/I4210159607"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22232","last_page":"22248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.45249998569488525,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.45249998569488525,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21089999377727509,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.15230000019073486,"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/graph","display_name":"Graph","score":0.48260000348091125},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.27000001072883606},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.2612999975681305},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.22750000655651093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087999939918518},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27549999952316284},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22750000655651093},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2264000028371811}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1211","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1211.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1211","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1211.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: EMNLP 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/W4416033916.pdf","grobid_xml":"https://content.openalex.org/works/W4416033916.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"has":[3,42],"emerged":[4],"as":[5,79],"a":[6,55,70,80],"promising":[7],"technique":[8],"to":[9,106,132,147],"enhance":[10],"the":[11,67,75,90,113,134,140,152],"quality":[12],"and":[13,40,73,77,86,99],"relevance":[14],"of":[15,115,142],"responses":[16],"generated":[17],"by":[18],"large":[19],"language":[20],"models.While":[21],"recent":[22],"advancements":[23],"have":[24],"mainly":[25],"focused":[26],"on":[27,34,151],"improving":[28],"RAG":[29,33,58],"for":[30,125],"text-based":[31],"queries,":[32],"multi-modal":[35,57,153],"documents":[36],"containing":[37],"both":[38,84],"texts":[39,76,100],"images":[41,78,98],"not":[43,50,94],"been":[44],"fully":[45],"explored.Especially":[46],"when":[47],"fine-tuning":[48],"does":[49],"work.This":[51],"paper":[52],"proposes":[53],"BRIT,":[54,116,143],"novel":[56],"framework":[59],"that":[60,130],"effectively":[61],"unifies":[62],"various":[63],"textimage":[64],"connections":[65],"in":[66,89],"document":[68],"into":[69],"multimodal":[71,126],"graph":[72],"retrieves":[74],"query-specific":[81],"sub-graph.By":[82],"traversing":[83],"image-to-text":[85],"text-to-image":[87],"paths":[88],"graph,":[91],"BRIT":[92],"retrieve":[93],"only":[95],"directly":[96],"query-relevant":[97],"but":[101],"also":[102],"further":[103],"relevant":[104],"contents":[105],"answering":[107,128],"complex":[108],"cross-modal":[109,149],"multi-hop":[110],"questions.To":[111],"evaluate":[112],"effectiveness":[114],"we":[117],"introduce":[118],"MM-RAG":[119],"1":[120],"test":[121],"set":[122],"specifically":[123],"designed":[124],"question":[127],"tasks":[129],"require":[131],"understand":[133],"text-image":[135],"relations.Our":[136],"comprehensive":[137],"experiments":[138],"demonstrate":[139],"superiority":[141],"highlighting":[144],"its":[145],"ability":[146],"handle":[148],"questions":[150],"documents.":[154]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-08T00:00:00"}