{"id":"https://openalex.org/W3195129957","doi":"https://doi.org/10.1145/3459637.3482218","title":"Lightweight Visual Question Answering using Scene Graphs","display_name":"Lightweight Visual Question Answering using Scene Graphs","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3195129957","doi":"https://doi.org/10.1145/3459637.3482218","mag":"3195129957"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ora.ox.ac.uk/objects/uuid:637e039f-0b2f-4353-8c68-7764b79e1a63","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008151704","display_name":"Sai Vidyaranya Nuthalapati","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sai Vidyaranya Nuthalapati","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030251358","display_name":"Ramraj Chandradevan","orcid":"https://orcid.org/0000-0001-9249-8843"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramraj Chandradevan","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102734034","display_name":"Eleonora Giunchiglia","orcid":"https://orcid.org/0000-0001-9313-753X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eleonora Giunchiglia","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387313","display_name":"Bowen Li","orcid":"https://orcid.org/0009-0006-7098-4043"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bowen Li","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064643004","display_name":"Maxime Kayser","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maxime Kayser","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091549352","display_name":"Thomas Lukasiewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lukasiewicz","raw_affiliation_strings":["Oxford University, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006897094","display_name":"Carl Yang","orcid":"https://orcid.org/0000-0001-9145-4531"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Yang","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008151704"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.4565,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.84247859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3353","last_page":"3357"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9927999973297119,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.8102872371673584},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7736718654632568},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6520847678184509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5665445923805237},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5165795087814331},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5034019351005554},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45946240425109863},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42352741956710815},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34831535816192627},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34819090366363525},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3178994655609131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102872371673584},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7736718654632568},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6520847678184509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5665445923805237},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5165795087814331},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5034019351005554},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45946240425109863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42352741956710815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34831535816192627},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34819090366363525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3178994655609131},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:637e039f-0b2f-4353-8c68-7764b79e1a63","is_oa":true,"landing_page_url":null,"pdf_url":"https://ora.ox.ac.uk/objects/uuid:637e039f-0b2f-4353-8c68-7764b79e1a63","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"}],"best_oa_location":{"id":"pmh:oai:ora.ox.ac.uk:uuid:637e039f-0b2f-4353-8c68-7764b79e1a63","is_oa":true,"landing_page_url":null,"pdf_url":"https://ora.ox.ac.uk/objects/uuid:637e039f-0b2f-4353-8c68-7764b79e1a63","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1093520412","display_name":null,"funder_award_id":"Scholarship","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3207594375","display_name":"DTP 2016-2017 University of Oxford","funder_award_id":"EP/N509711/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5267675942","display_name":"RealPDBs: Realistic Data Models and Query Compilation for Large-Scale Probabilistic Databases","funder_award_id":"EP/R013667/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6120213013","display_name":null,"funder_award_id":"EP/R013667/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6641252456","display_name":null,"funder_award_id":"EP/P020275/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8597009950","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8648918050","display_name":null,"funder_award_id":"2052861","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8666754563","display_name":"JADE: Joint Academic Data science Endeavour","funder_award_id":"EP/P020275/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8719353587","display_name":null,"funder_award_id":"EP/P0","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320321048","display_name":"AXA Research Fund","ror":"https://ror.org/02zxqxw53"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195129957.pdf","grobid_xml":"https://content.openalex.org/works/W3195129957.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1536680647","https://openalex.org/W1933349210","https://openalex.org/W2277195237","https://openalex.org/W2519887557","https://openalex.org/W2561715562","https://openalex.org/W2624431344","https://openalex.org/W2786915849","https://openalex.org/W2811124557","https://openalex.org/W2886970679","https://openalex.org/W2950761309","https://openalex.org/W2951343884","https://openalex.org/W2951619830","https://openalex.org/W2951901104","https://openalex.org/W2962749469","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963415211","https://openalex.org/W2963449176","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963858333","https://openalex.org/W2963938081","https://openalex.org/W2964138343","https://openalex.org/W2964308564","https://openalex.org/W2971081194","https://openalex.org/W2990397898","https://openalex.org/W2997342017","https://openalex.org/W3004349648","https://openalex.org/W3025726122","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3114303065","https://openalex.org/W3127524795","https://openalex.org/W3202514640","https://openalex.org/W4210257598","https://openalex.org/W6600076646"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W2914694625","https://openalex.org/W4297783004","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Visual":[0],"question":[1,109],"answering":[2],"(VQA)":[3],"is":[4,103,192],"a":[5,13,77,107,206],"challenging":[6],"problem":[7],"in":[8,50,133],"machine":[9,179],"perception,":[10],"which":[11,102,181],"requires":[12],"deep":[14],"joint":[15],"understanding":[16],"of":[17,30,90,123,151,166,172],"both":[18,97],"visual":[19,91],"and":[20,68,92,99,142],"textual":[21,108],"data.":[22,54],"Recent":[23],"research":[24],"has":[25],"advanced":[26],"the":[27,62,120,134,147,152,164,170,173,176],"automatic":[28],"generation":[29,67],"high-quality":[31],"scene":[32,65,94,135,161,188],"graphs":[33,95,136],"from":[34],"images,":[35],"while":[36],"powerful":[37],"yet":[38],"elegant":[39],"models":[40],"like":[41],"graph":[42,66,140],"neural":[43,177],"networks":[44],"(GNNs)":[45],"have":[46],"shown":[47],"great":[48],"power":[49],"reasoning":[51],"over":[52],"graph-structured":[53],"In":[55,73],"this":[56],"work,":[57],"we":[58,75,127,145],"propose":[59],"to":[60,87,111,118],"bridge":[61],"gap":[63],"between":[64],"VQA":[69,155,198],"by":[70,185],"leveraging":[71,186],"GNNs.":[72],"particular,":[74],"design":[76],"new":[78],"model":[79],"called":[80],"Conditional":[81],"Enhanced":[82],"Graph":[83],"ATtention":[84],"network":[85],"(CE-GAT)":[86],"encode":[88],"pairs":[89],"semantic":[93],"with":[96,106,159,169,196],"node":[98],"edge":[100],"features,":[101],"seamlessly":[104],"integrated":[105],"encoder":[110],"generate":[112],"answers":[113],"through":[114,137],"question-graph":[115],"conditioning.":[116],"Moreover,":[117],"alleviate":[119],"training":[121],"difficulties":[122],"CE-GAT":[124],"towards":[125],"VQA,":[126],"enforce":[128],"more":[129],"useful":[130],"inductive":[131],"biases":[132],"novel":[138],"question-guided":[139],"enriching":[141],"pruning.":[143],"Finally,":[144],"evaluate":[146],"framework":[148,191],"on":[149],"one":[150],"largest":[153],"available":[154],"datasets":[156],"(namely,":[157,175],"GQA)":[158],"ground-truth":[160],"graphs,":[162,189],"achieving":[163],"accuracy":[165],"77.87%,":[167],"compared":[168,195],"state":[171,178],"art":[174],"(NSM)),":[180],"gives":[182],"63.17%.":[183],"Notably,":[184],"existing":[187],"our":[190],"much":[193],"lighter":[194],"end-to-end":[197],"methods":[199],"(e.g.,":[200],"about":[201],"95.3%":[202],"less":[203],"parameters":[204],"than":[205],"typical":[207],"NSM).":[208]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}