{"id":"https://openalex.org/W2916723116","doi":"https://doi.org/10.1109/cvpr.2019.00209","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","display_name":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2916723116","doi":"https://doi.org/10.1109/cvpr.2019.00209","mag":"2916723116"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2019.00209","doi":"https://doi.org/10.1109/cvpr.2019.00209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00209","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.09487","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036295862","display_name":"R\u00e9mi Cad\u00e8ne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remi Cadene","raw_affiliation_strings":["Sorbonne université"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne université","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037212744","display_name":"Hedi Ben-younes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hedi Ben-younes","raw_affiliation_strings":["LIP6","Heuritech, Paris","Sorbonne Universit\u00e9, CNRS, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIP6","institution_ids":["https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Heuritech, Paris","institution_ids":[]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Paris","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108118084","display_name":"Matthieu Cord","orcid":"https://orcid.org/0000-0002-0627-5844","observed_orcids":["https://orcid.org/0000-0002-0627-5844"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Cord","raw_affiliation_strings":["Sorbonne Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Univ","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017490804","display_name":"Nicolas Thome","orcid":"https://orcid.org/0000-0003-4871-3045","observed_orcids":["https://orcid.org/0000-0003-4871-3045"]},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Thome","raw_affiliation_strings":["CNAM, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNAM, Paris","institution_ids":["https://openalex.org/I124158823"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.7825,"has_fulltext":true,"cited_by_count":339,"citation_normalized_percentile":{"value":0.99180743,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2019","issue":null,"first_page":"1989","last_page":"1998"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.9909999966621399},{"id":"https://openalex.org/keywords/relational-networks","display_name":"relational networks","score":0.6309999823570251},{"id":"https://openalex.org/keywords/attention-network","display_name":"attentional networks","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181979656219482},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7864686250686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050139665603638},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5999510288238525},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5917838215827942},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.534845769405365},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5255452394485474},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5218138694763184},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5187690258026123},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5134366750717163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38437628746032715},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cvpr.2019.00209","doi":"https://doi.org/10.1109/cvpr.2019.00209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00209","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.09487","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09487","pdf_url":"https://arxiv.org/pdf/1902.09487","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-02073649v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-02073649","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2019, Long Beach, CA, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1902.09487","doi":"https://doi.org/10.48550/arxiv.1902.09487","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.09487","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3175797963","doi":null,"is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/detail?JGLOBAL_ID=202002232844726516","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.09487","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09487","pdf_url":"https://arxiv.org/pdf/1902.09487","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3964255678","display_name":"Machine learning with deep neural networks","funder_award_id":"ANR-16-CE23-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2916723116.pdf","grobid_xml":"https://content.openalex.org/works/W2916723116.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W2133564696","https://openalex.org/W2151498684","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2404287312","https://openalex.org/W2439787475","https://openalex.org/W2479423890","https://openalex.org/W2522258376","https://openalex.org/W2532034655","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2597425697","https://openalex.org/W2613404084","https://openalex.org/W2616125804","https://openalex.org/W2624614404","https://openalex.org/W2738853914","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2760103357","https://openalex.org/W2768661419","https://openalex.org/W2770129969","https://openalex.org/W2771951981","https://openalex.org/W2786209943","https://openalex.org/W2787119853","https://openalex.org/W2793546384","https://openalex.org/W2795434624","https://openalex.org/W2804180102","https://openalex.org/W2804243936","https://openalex.org/W2805516822","https://openalex.org/W2808877322","https://openalex.org/W2884093133","https://openalex.org/W2885380450","https://openalex.org/W2894842749","https://openalex.org/W2962933067","https://openalex.org/W2963055199","https://openalex.org/W2963150162","https://openalex.org/W2963223524","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963770662","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964094751","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W4249013746","https://openalex.org/W6753027577"],"related_works":["https://openalex.org/W3037773948","https://openalex.org/W4200506418","https://openalex.org/W3163363326","https://openalex.org/W3157224510","https://openalex.org/W2969332757","https://openalex.org/W4307818888","https://openalex.org/W4387675775","https://openalex.org/W4386703217","https://openalex.org/W3007556011","https://openalex.org/W3216294399"],"abstract_inverted_index":{"Multimodal":[0],"attentional":[1],"networks":[2],"are":[3],"currently":[4],"state-of-the-art":[5,165],"models":[6],"for":[7,41],"Visual":[8],"Question":[9],"Answering":[10],"(VQA)":[11],"tasks":[12],"involving":[13],"real":[14,64],"images.":[15,65],"Although":[16],"attention":[17,127],"allows":[18],"to":[19,26,35,61,120,144,162],"focus":[20],"on":[21,147],"the":[22,27,70,73,102,131],"visual":[23,112],"content":[24],"relevant":[25],"question,":[28],"this":[29,48,168],"simple":[30],"mechanism":[31],"is":[32,58,69,160,173],"arguably":[33],"insufficient":[34],"model":[36],"complex":[37],"reasoning":[38,78],"features":[39],"required":[40],"VQA":[42,150],"or":[43,163],"other":[44],"high-level":[45],"tasks.":[46],"In":[47],"paper,":[49],"we":[50,100],"propose":[51],"MuRel,":[52],"a":[53,88,105],"multimodal":[54],"relational":[55],"network":[56,159],"which":[57,109],"learned":[59],"end-to-end":[60],"reason":[62],"over":[63],"Our":[66,156,171],"first":[67],"contribution":[68],"introduction":[71],"of":[72,133],"MuRel":[74,107,158],"cell,":[75],"an":[76],"atomic":[77],"primitive":[79],"representing":[80],"interactions":[81],"between":[82],"question":[83,114],"and":[84,92,113,116,140,154],"image":[85],"regions":[86],"by":[87],"rich":[89],"vectorial":[90],"representation,":[91],"modeling":[93],"region":[94],"relations":[95],"with":[96,136],"pairwise":[97],"combinations.":[98],"Secondly,":[99],"incorporate":[101],"cell":[103],"into":[104],"full":[106],"network,":[108],"progressively":[110],"refines":[111],"interactions,":[115],"can":[117],"be":[118],"leveraged":[119],"define":[121],"visualization":[122],"schemes":[123],"finer":[124],"than":[125],"mere":[126],"maps.":[128],"We":[129],"validate":[130],"relevance":[132],"our":[134],"approach":[135],"various":[137],"ablation":[138],"studies,":[139],"show":[141],"its":[142],"superiority":[143],"attention-based":[145],"methods":[146],"three":[148],"datasets:":[149],"2.0,":[151],"VQA-CP":[152],"v2":[153],"TDIUC.":[155],"final":[157],"competitive":[161],"outperforms":[164],"results":[166],"in":[167],"challenging":[169],"context.":[170],"code":[172],"available:":[174],"github.com/Cadene/murel.bootstrap.pytorch":[175]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":64},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":71},{"year":2019,"cited_by_count":14}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-03-02T00:00:00"}