{"id":"https://openalex.org/W4407989236","doi":"https://doi.org/10.1145/3805712.3808615","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","display_name":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W4407989236","doi":"https://doi.org/10.1145/3805712.3808615"},"language":"en","primary_location":{"id":"doi:10.1145/3805712.3808615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808615","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087152286","display_name":"Yin Wu","orcid":"https://orcid.org/0000-0002-6364-4597"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yin Wu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-9041-5452","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quanyu Long","orcid":"https://orcid.org/0000-0002-4839-012X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Quanyu Long","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4839-012X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367188","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-2256-9818"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3262-3734","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102298336","display_name":"Jianfei Yu","orcid":null},"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":"Jianfei Yu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8380-0609","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/A5101936536","display_name":"Wenya Wang","orcid":"https://orcid.org/0000-0003-2624-5498"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenya Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5612-7818","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00436475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3473","last_page":"3480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9962999820709229,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9922000169754028,"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/benchmarking","display_name":"Benchmarking","score":0.8453633785247803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5530814528465271},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5312233567237854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5045892000198364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2731114625930786},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.23358342051506042},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.04839220643043518}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8453633785247803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5530814528465271},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5312233567237854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5045892000198364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2731114625930786},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.23358342051506042},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.04839220643043518}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3805712.3808615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808615","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.16636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.16636","pdf_url":"https://arxiv.org/pdf/2502.16636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2502.16636","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.16636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808615","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"augments":[3],"large":[4],"language":[5],"models":[6,39,142],"(LLMs)":[7],"with":[8],"external":[9],"knowledge":[10,104],"to":[11,144],"tackle":[12],"knowledge-intensive":[13,64,76],"question":[14],"answering.":[15],"While":[16],"several":[17],"benchmarks":[18],"evaluate":[19,112],"multimodal":[20,24,138,175],"LLMs":[21],"(MLLMs)":[22],"under":[23,158],"RAG":[25,65],"settings,":[26],"they":[27],"predominantly":[28],"retrieve":[29],"from":[30],"textual":[31],"corpora":[32],"and":[33,54,90,115,119,146,151,172],"do":[34],"not":[35],"explicitly":[36,100],"assess":[37],"how":[38],"exploit":[40,147],"visual":[41,63,80,103,128,149,169],"evidence":[42,139],"during":[43],"answer":[44,107],"generation.":[45,108],"Consequently,":[46],"there":[47],"still":[48,124],"lacks":[49],"benchmark":[50,72],"that":[51,73,121],"cleanly":[52],"isolates":[53],"measures":[55],"the":[56,91,102,127,165],"contribution":[57],"of":[58,93],"retrieved":[59,94,132],"images":[60,96],"in":[61,78,131,174],"a":[62,70,79],"pipeline.":[66],"We":[67],"introduce":[68],"Visual-RAG,":[69,110],"question-answering":[71],"targets":[74],"visually-grounded,":[75],"questions":[77],"evidence-centric":[81],"manner.":[82],"Unlike":[83],"prior":[84],"work,":[85],"Visual-RAG":[86,177],"requires":[87],"text-to-image":[88,152],"retrieval":[89,153],"integration":[92],"clue":[95],"whose":[97],"pixel":[98],"content":[99],"encodes":[101],"necessary":[105],"for":[106,137,167],"With":[109],"we":[111],"five":[113],"open-source":[114],"three":[116],"proprietary":[117],"MLLMs":[118],"find":[120],"current":[122],"systems":[123],"substantially":[125],"underutilize":[126],"information":[129],"available":[130,180],"images.":[133],"Despite":[134],"clear":[135],"opportunities":[136],"integration,":[140],"state-of-the-art":[141],"struggle":[143],"extract":[145],"fine-grained":[148],"knowledge,":[150],"itself":[154],"remains":[155],"challenging":[156],"even":[157],"constrained":[159],"entity-level":[160],"corpora.":[161],"These":[162],"results":[163],"underscore":[164],"need":[166],"improved":[168],"retrieval,":[170],"grounding,":[171],"attribution":[173],"RAG.":[176],"is":[178],"publicly":[179],"at:":[181],"github.com/visual-rag/visual-rag":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}