{"id":"https://openalex.org/W4385682832","doi":"https://doi.org/10.1145/3581783.3611964","title":"Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","display_name":"Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385682832","doi":"https://doi.org/10.1145/3581783.3611964"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100379388","display_name":"Qian Yang","orcid":"https://orcid.org/0009-0009-8975-6982"},"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":true,"raw_author_name":"Qian Yang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428431","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0001-6939-7438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Unaffiliated, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Unaffiliated, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Unaffiliated, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Unaffiliated, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083079672","display_name":"Baotian Hu","orcid":"https://orcid.org/0000-0001-7490-684X"},"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":"Baotian Hu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100379388"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2098,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83220592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5223","last_page":"5234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8755005598068237},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6924080848693848},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6178074479103088},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5365192294120789},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.517092227935791},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4337530732154846},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4114561080932617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35711854696273804},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0931563675403595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755005598068237},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6924080848693848},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6178074479103088},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5365192294120789},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.517092227935791},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4337530732154846},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4114561080932617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35711854696273804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0931563675403595},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3570341100","display_name":null,"funder_award_id":"62006061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6163091765","display_name":null,"funder_award_id":"2020010","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":31,"referenced_works":["https://openalex.org/W2080133951","https://openalex.org/W2194775991","https://openalex.org/W2595551253","https://openalex.org/W2608309533","https://openalex.org/W2953867581","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963323070","https://openalex.org/W2963563735","https://openalex.org/W2970959783","https://openalex.org/W2981852735","https://openalex.org/W2998374885","https://openalex.org/W3034727271","https://openalex.org/W3034999214","https://openalex.org/W3091588028","https://openalex.org/W3173220247","https://openalex.org/W3176456866","https://openalex.org/W3182778088","https://openalex.org/W3186545525","https://openalex.org/W3190126809","https://openalex.org/W3207796810","https://openalex.org/W3210877910","https://openalex.org/W4221166835","https://openalex.org/W4226278471","https://openalex.org/W4281254837","https://openalex.org/W4285249364","https://openalex.org/W4288089799","https://openalex.org/W4312643954","https://openalex.org/W4385572953","https://openalex.org/W4385573853","https://openalex.org/W6600351811"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2185469136","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Multi-modal":[0],"multi-hop":[1,133],"question":[2,7],"answering":[3,5],"involves":[4],"a":[6,26,80,106],"by":[8],"reasoning":[9],"over":[10],"multiple":[11],"input":[12],"sources":[13,96],"from":[14,97],"different":[15,98],"modalities.":[16],"Existing":[17],"methods":[18],"often":[19],"retrieve":[20],"evidences":[21],"separately":[22],"and":[23,38,45,61,83,118,137,150],"then":[24,104],"use":[25],"language":[27],"model":[28,49],"to":[29,48,94,110],"generate":[30],"an":[31,90],"answer":[32,116,151],"based":[33],"on":[34,129],"the":[35,50,56,122,143],"retrieved":[36],"evidences,":[37],"thus":[39],"do":[40],"not":[41],"adequately":[42],"connect":[43],"candidates":[44],"are":[46],"unable":[47],"interdependent":[51],"relations":[52],"during":[53],"retrieval.":[54],"Moreover,":[55],"pipelined":[57],"approaches":[58],"of":[59,124],"retrieval":[60,70,113,125,149],"generation":[62,67,117,152],"might":[63],"result":[64],"in":[65,146],"poor":[66],"performance":[68,71,153],"when":[69],"is":[72],"low.":[73],"To":[74],"address":[75],"these":[76],"issues,":[77],"we":[78],"propose":[79],"Structured":[81],"Knowledge":[82],"Unified":[84],"Retrieval-Generation":[85,108],"(SKURG)":[86],"approach.":[87],"SKURG":[88,141],"employs":[89],"Entity-centered":[91],"Fusion":[92],"Encoder":[93],"align":[95],"modalities":[99],"using":[100],"shared":[101],"entities.":[102],"It":[103],"uses":[105],"unified":[107],"Decoder":[109],"integrate":[111],"intermediate":[112],"results":[114],"for":[115],"also":[119],"adaptively":[120],"determine":[121],"number":[123],"steps.":[126],"Extensive":[127],"experiments":[128],"two":[130],"representative":[131],"multi-modal":[132],"QA":[134],"datasets":[135],"MultimodalQA":[136],"WebQA":[138],"demonstrate":[139],"that":[140],"outperforms":[142],"state-of-the-art":[144],"models":[145],"both":[147],"source":[148],"with":[154],"fewer":[155],"parameters1.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-08-09T00:00:00"}