{"id":"https://openalex.org/W4417072983","doi":"https://doi.org/10.1145/3743093.3771062","title":"Global Question-Aware Multimodal Retrieval-Augmented Generation for Multimedia Multi-Hop Question Answering","display_name":"Global Question-Aware Multimodal Retrieval-Augmented Generation for Multimedia Multi-Hop Question Answering","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417072983","doi":"https://doi.org/10.1145/3743093.3771062"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771062","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhixiao Shen","orcid":"https://orcid.org/0009-0002-6697-0432"},"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":"Zhixiao Shen","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-6697-0432","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084990301","display_name":"Jianfei Yu","orcid":"https://orcid.org/0000-0001-8380-0609"},"institutions":[{"id":"https://openalex.org/I131434179","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19","country_code":"CN","type":"education","lineage":["https://openalex.org/I131434179"]},{"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 and University of Chinese Academy of Sciences, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8380-0609","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China and University of Chinese Academy of Sciences, Nanjing, China","institution_ids":["https://openalex.org/I131434179","https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078565848","display_name":"Wenya Wang","orcid":"https://orcid.org/0000-0001-5612-7818"},"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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058"},"institutions":[{"id":"https://openalex.org/I131434179","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19","country_code":"CN","type":"education","lineage":["https://openalex.org/I131434179"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["Nanjing University, Nanjing, China and University of Chinese Academy of Sciences, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0621-1058","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China and University of Chinese Academy of Sciences, Nanjing, China","institution_ids":["https://openalex.org/I131434179"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44857554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.40310001373291016,"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":0.40310001373291016,"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/T10028","display_name":"Topic Modeling","score":0.38960000872612,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.05920000001788139,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/question-answering","display_name":"Question answering","score":0.567300021648407},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.32280001044273376},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3018999993801117},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2637999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771062","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6784231808","display_name":null,"funder_award_id":"62476132,62476134","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417072983.pdf","grobid_xml":"https://content.openalex.org/works/W4417072983.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W4226278471","https://openalex.org/W4252076394","https://openalex.org/W4285249364","https://openalex.org/W4375958382","https://openalex.org/W4385571810","https://openalex.org/W4385573236","https://openalex.org/W4385682832","https://openalex.org/W4387969587","https://openalex.org/W4390479156","https://openalex.org/W4390479160","https://openalex.org/W4390523405","https://openalex.org/W4390523442","https://openalex.org/W4395686609","https://openalex.org/W4397028865","https://openalex.org/W4402345917","https://openalex.org/W4402671532","https://openalex.org/W4402671780","https://openalex.org/W4403995577","https://openalex.org/W4404545360","https://openalex.org/W4405869274"],"related_works":[],"abstract_inverted_index":{"Multimedia":[0],"Multi-Hop":[1],"Question":[2],"Answering":[3],"(MMQA)":[4],"is":[5,163],"a":[6,36,87,113,147,168],"complex":[7],"task":[8],"that":[9,31,203],"requires":[10],"models":[11],"to":[12,28,70,90,122,132,145,174,179],"reason":[13],"over":[14],"and":[15,23,59,94,131,139,158,190],"integrate":[16],"information":[17,51,136],"from":[18,44,72],"both":[19],"visual":[20],"(e.g.,":[21,25],"images)":[22],"textual":[24],"documents)":[26],"modalities":[27],"answer":[29,178],"questions":[30,130,157],"cannot":[32],"be":[33],"resolved":[34],"in":[35],"single":[37],"step.":[38],"Existing":[39],"methods":[40,209],"for":[41,98],"MMQA":[42,200],"suffer":[43],"two":[45,104,198],"common":[46],"limitations:":[47],"(1)":[48,107],"insufficient":[49],"cross-modal":[50,92,125,142],"fusion,":[52],"which":[53],"restricts":[54],"interaction":[55],"between":[56,154],"different":[57],"modalities;":[58],"(2)":[60,140],"weak":[61],"global":[62,114],"understanding":[63],"of":[64],"multi-hop":[65,99,128],"questions,":[66],"making":[67],"them":[68],"vulnerable":[69],"distractions":[71],"intermediate":[73,188],"steps.":[74],"To":[75],"address":[76],"these":[77],"challenges,":[78],"we":[79],"introduce":[80],"Global":[81],"question-aware":[82],"Multimodal":[83,169],"Retrieval-Augmented":[84],"Generation":[85],"(GMRAG),":[86],"framework":[88],"designed":[89],"enhance":[91],"reasoning":[93,126],"improve":[95],"retrieval":[96,117],"precision":[97],"multimodal":[100,129,156],"questions.":[101],"It":[102],"brings":[103],"core":[105],"innovations:":[106],"restructuring":[108],"the":[109,120,176,180],"training":[110],"data":[111],"into":[112,167],"question\u2013aware,":[115],"evidence-centric":[116],"dataset,":[118],"enabling":[119],"retriever":[121],"perform":[123],"richer":[124],"on":[127,185,197],"identify":[133],"globally":[134],"relevant":[135],"more":[137],"effectively;":[138],"employing":[141],"contrastive":[143],"learning":[144],"fine-tune":[146],"joint":[148],"image\u2013text":[149],"encoder,":[150],"achieving":[151],"stronger":[152],"alignment":[153],"holistic":[155],"evidence.":[159],"The":[160],"retrieved":[161],"evidence":[162],"then":[164],"directly":[165],"fed":[166],"Large":[170],"Language":[171],"Models":[172],"(MLLMs)":[173],"generate":[175],"final":[177],"original":[181],"question,":[182],"eliminating":[183],"dependence":[184],"potentially":[186],"flawed":[187],"answers":[189],"thus":[191],"mitigating":[192],"error":[193],"propagation.":[194],"Experimental":[195],"results":[196],"public":[199],"datasets":[201],"show":[202],"GMRAG":[204],"consistently":[205],"outperforms":[206],"existing":[207],"RAG":[208],"across":[210],"various":[211],"MLLMs.":[212]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-12-06T00:00:00"}