{"id":"https://openalex.org/W2803686446","doi":"https://doi.org/10.1145/3219819.3220036","title":"R-VQA","display_name":"R-VQA","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2803686446","doi":"https://doi.org/10.1145/3219819.3220036","mag":"2803686446"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3220036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.09701","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pan Lu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ji","raw_affiliation_strings":["Microsoft Research Asia &Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia &Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nan Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["Microsoft Research Asia &Microsoft Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia &Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research Asia &Microsoft Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia &Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jianyong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyong Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.8291,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95296161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1880","last_page":"1889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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/relation","display_name":"Relation (database)","score":0.7053999900817871},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5152999758720398},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4659000039100647},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.44769999384880066},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44440001249313354},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4138999879360199},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39250001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421000003814697},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7053999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3219819.3220036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.09701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.09701","pdf_url":"https://arxiv.org/pdf/1805.09701","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.09701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.09701","pdf_url":"https://arxiv.org/pdf/1805.09701","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2001773889","https://openalex.org/W2064675550","https://openalex.org/W2094728533","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2347817542","https://openalex.org/W2510976782","https://openalex.org/W2565085003","https://openalex.org/W2605736949","https://openalex.org/W2732016772","https://openalex.org/W2743904806","https://openalex.org/W2757442264","https://openalex.org/W2789120929","https://openalex.org/W2963650529","https://openalex.org/W2963656855","https://openalex.org/W2963954913","https://openalex.org/W2964138017"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Visual":[1,121],"Question":[2],"Answering":[3],"(VQA)":[4],"has":[5],"emerged":[6],"as":[7,17,65],"one":[8],"of":[9,134,169,204],"the":[10,70,83,120,189,202],"most":[11],"significant":[12],"tasks":[13],"in":[14,61,96,129],"multimodal":[15,43],"learning":[16],"it":[18],"requires":[19],"understanding":[20],"both":[21],"visual":[22,105,157,170,179,206],"and":[23,33,86,143,172,181,200],"textual":[24],"modalities.":[25],"Existing":[26],"methods":[27],"mainly":[28],"rely":[29],"on":[30,119,188],"extracting":[31],"image":[32],"question":[34],"features":[35],"to":[36,55,69,82,103,155,176],"learn":[37,104],"their":[38],"joint":[39],"feature":[40],"embedding":[41],"via":[42,124],"fusion":[44],"or":[45,59,77],"attention":[46,166,171,174],"mechanism.":[47],"Some":[48],"recent":[49],"studies":[50],"utilize":[51,93],"external":[52],"VQA-independent":[53],"models":[54],"detect":[56],"candidate":[57,75],"entities":[58,76],"attributes":[60,78],"images,":[62,97],"which":[63,130],"serve":[64],"semantic":[66,89,94,126,173,182],"knowledge":[67,95,180],"complementary":[68],"VQA":[71,84],"task.":[72],"However,":[73],"these":[74],"might":[79],"be":[80],"unrelated":[81],"task":[85],"have":[87],"limited":[88],"capacities.":[90],"To":[91],"better":[92],"we":[98,111],"propose":[99,163],"a":[100,114,125,137,140,144,164],"novel":[101],"framework":[102],"relation":[106,146,150,159,207],"facts":[107],"for":[108],"VQA.":[109],"Specifically,":[110],"build":[112],"up":[113],"Relation-VQA":[115],"(R-VQA)":[116],"dataset":[117,123],"based":[118],"Genome":[122],"similarity":[127],"module,":[128],"each":[131],"data":[132],"consists":[133],"an":[135],"image,":[136],"corresponding":[138],"question,":[139],"correct":[141],"answer":[142],"supporting":[145],"fact.":[147],"A":[148],"well-defined":[149],"detector":[151],"is":[152],"then":[153],"adopted":[154],"predict":[156],"question-related":[158],"facts.":[160,208],"We":[161,184],"further":[162],"multi-step":[165],"model":[167,196],"composed":[168],"sequentially":[175],"extract":[177],"related":[178],"knowledge.":[183],"conduct":[185],"comprehensive":[186],"experiments":[187],"two":[190],"benchmark":[191],"datasets,":[192],"demonstrating":[193],"that":[194],"our":[195],"achieves":[197],"state-of-the-art":[198],"performance":[199],"verifying":[201],"benefit":[203],"considering":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-06-01T00:00:00"}