{"id":"https://openalex.org/W2904742344","doi":"https://doi.org/10.1609/aaai.v33i01.33018102","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","display_name":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904742344","doi":"https://doi.org/10.1609/aaai.v33i01.33018102","mag":"2904742344"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018102","doi":"https://doi.org/10.1609/aaai.v33i01.33018102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018102","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33018102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037212744","display_name":"Hedi Ben-younes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"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":"Hedi Ben-younes","raw_affiliation_strings":["Sorbonne Universit\u00e9","Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036295862","display_name":"R\u00e9mi Cad\u00e8ne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"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 Universit\u00e9","Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","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":["National Conservatory of Arts and Crafts","Conservatoire National des Arts et M\u00e9tiers, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Conservatory of Arts and Crafts","institution_ids":["https://openalex.org/I124158823"]},{"raw_affiliation_string":"Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]}]},{"author_position":"last","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/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"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 Universit\u00e9","Universit\u00e9 Paris Cit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9399,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90997659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"8102","last_page":"8109"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"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/multimodal-fusion","display_name":"multimodal fusion","score":0.9490000009536743},{"id":"https://openalex.org/keywords/bilinear-model","display_name":"bilinear model","score":0.7839999794960022},{"id":"https://openalex.org/keywords/tensor-rank","display_name":"tensor rank","score":0.6060000061988831},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.9169999957084656},{"id":"https://openalex.org/keywords/visual-relationship-detection","display_name":"visual relationship detection","score":0.9959999918937683},{"id":"https://openalex.org/keywords/cross-modal-interaction","display_name":"cross-modal interaction","score":0.5419999957084656},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199194431304932},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6561682820320129},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6268202066421509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708860158920288},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5126554369926453},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5098084807395935},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4742804169654846},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.45080843567848206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40760788321495056},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3890071511268616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11372986435890198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11284583806991577},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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:10.1609/aaai.v33i01.33018102","doi":"https://doi.org/10.1609/aaai.v33i01.33018102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018102","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1902.00038","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.00038","pdf_url":"https://arxiv.org/pdf/1902.00038","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-02073644v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-02073644","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":"AAAI 2019 - 33rd AAAI Conference on Artificial Intelligence, Jan 2019, Honolulu, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1902.00038","doi":"https://doi.org/10.48550/arxiv.1902.00038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.00038","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2904742344","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/1902.00038","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Vision and Pattern Recognition","raw_type":null}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018102","doi":"https://doi.org/10.1609/aaai.v33i01.33018102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018102","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1189697078","display_name":null,"funder_award_id":"ANR\u201311\u2013LABX\u201365","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904742344.pdf","grobid_xml":"https://content.openalex.org/works/W2904742344.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1933349210","https://openalex.org/W1963826206","https://openalex.org/W2000045479","https://openalex.org/W2000215628","https://openalex.org/W2119412403","https://openalex.org/W2416885651","https://openalex.org/W2439787475","https://openalex.org/W2479423890","https://openalex.org/W2532034655","https://openalex.org/W2560730294","https://openalex.org/W2591644541","https://openalex.org/W2597425697","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2616125804","https://openalex.org/W2736330435","https://openalex.org/W2738853914","https://openalex.org/W2740962769","https://openalex.org/W2742274851","https://openalex.org/W2745132836","https://openalex.org/W2747623286","https://openalex.org/W2753474648","https://openalex.org/W2787119853","https://openalex.org/W2795434624","https://openalex.org/W2962737704","https://openalex.org/W2963055199","https://openalex.org/W2963150162","https://openalex.org/W2963650529"],"related_works":["https://openalex.org/W2616125804","https://openalex.org/W2969699701","https://openalex.org/W2969332757","https://openalex.org/W2964904918","https://openalex.org/W2747623286","https://openalex.org/W6940938567","https://openalex.org/W2963150162","https://openalex.org/W4409320555","https://openalex.org/W2903867219","https://openalex.org/W3107273227"],"abstract_inverted_index":{"Multimodal":[0],"representation":[1],"learning":[2,12,44],"is":[3,106,181],"gaining":[4],"more":[5,7],"and":[6,76,99,105,140,176],"interest":[8,124],"within":[9,41],"the":[10,34,59,65,94,97,102,122],"deep":[11,43],"community.":[13],"While":[14],"bilinear":[15],"models":[16,172],"provide":[17],"an":[18],"interesting":[19],"framework":[20],"to":[21,88,108,168],"find":[22],"subtle":[23],"combination":[24],"of":[25,29,67,74,101,125],"modalities,":[26],"their":[27,38],"number":[28],"parameters":[30],"grows":[31],"quadratically":[32],"with":[33,166],"input":[35],"dimensions,":[36],"making":[37],"practical":[39,123],"implementation":[40],"classical":[42],"pipelines":[45],"challenging.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,146,160],"introduce":[51],"BLOCK,":[52],"a":[53],"new":[54,90],"multimodal":[55,84,170],"fusion":[56,103,127,171],"based":[57],"on":[58],"block-superdiagonal":[60],"tensor":[61],"decomposition.":[62],"It":[63,86],"leverages":[64],"notion":[66],"block-term":[68],"ranks,":[69],"which":[70],"generalizes":[71],"both":[72,174],"concepts":[73],"rank":[75],"mode":[77],"ranks":[78],"for":[79,83,92,132,151,173],"tensors,":[80],"already":[81],"used":[82],"fusion.":[85],"allows":[87],"define":[89],"ways":[91],"optimizing":[93],"tradeoff":[95],"between":[96,113,155],"expressiveness":[98],"complexity":[100],"model,":[104],"able":[107],"represent":[109],"very":[110],"fine":[111],"interactions":[112,154],"modalities":[114],"while":[115],"maintaining":[116],"powerful":[117],"mono-modal":[118],"representations.":[119],"We":[120],"demonstrate":[121],"our":[126],"model":[128],"by":[129],"using":[130],"BLOCK":[131,163],"two":[133],"challenging":[134],"tasks:":[135],"Visual":[136,141],"Question":[137],"Answering":[138],"(VQA)":[139],"Relationship":[142],"Detection":[143],"(VRD),":[144],"where":[145],"design":[147],"end-to-end":[148],"learnable":[149],"architectures":[150],"representing":[152],"relevant":[153],"modalities.":[156],"Through":[157],"extensive":[158],"experiments,":[159],"show":[161],"that":[162],"compares":[164],"favorably":[165],"respect":[167],"state-of-the-art":[169],"VQA":[175],"VRD":[177],"tasks.":[178],"Our":[179],"code":[180],"available":[182],"at":[183],"https://github.com/Cadene/block.bootstrap.pytorch.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-12-22T00:00:00"}