{"id":"https://openalex.org/W3045355015","doi":"https://doi.org/10.1007/978-3-030-58545-7_41","title":"Spatially Aware Multimodal Transformers for TextVQA","display_name":"Spatially Aware Multimodal Transformers for TextVQA","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3045355015","doi":"https://doi.org/10.1007/978-3-030-58545-7_41","mag":"3045355015"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-58545-7_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-58545-7_41","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.12146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065406640","display_name":"Yash Kant","orcid":"https://orcid.org/0009-0002-8347-4895"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yash Kant","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia","georgia institute of technology, atlanta, georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"georgia institute of technology, atlanta, georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Facebook AI Research (FAIR), New York City, USA","Georgia Institute of Technology, Atlanta, Georgia","Facebook AI Research (FAIR)","Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research (FAIR), New York City, USA","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Facebook AI Research (FAIR)","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020091255","display_name":"Peter Anderson","orcid":"https://orcid.org/0000-0002-6359-8586"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Anderson","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia","georgia institute of technology, atlanta, georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"georgia institute of technology, atlanta, georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069704585","display_name":"Alex Schwing","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Schwing","raw_affiliation_strings":["University of Illinois, Urbana, Champaign, USA","University of Illinois; Champaign USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois; Champaign USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Devi Parikh","raw_affiliation_strings":["Facebook AI Research (FAIR), New York City, USA","Georgia Institute of Technology, Atlanta, Georgia","Georgia Institute of Technology","Facebook AI Research (FAIR)"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research (FAIR), New York City, USA","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Facebook AI Research (FAIR)","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101055775","display_name":"Jiasen Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiasen Lu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia","georgia institute of technology, atlanta, georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"georgia institute of technology, atlanta, georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072335131","display_name":"Harsh Agrawal","orcid":"https://orcid.org/0000-0003-4147-5953"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsh Agrawal","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia","georgia institute of technology, atlanta, georgia"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"georgia institute of technology, atlanta, georgia","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5065406640"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.126,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48887647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"715","last_page":"732"},"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.7951809167861938},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7548590302467346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661361217498779},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48342931270599365},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.47564244270324707},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.47328728437423706},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4729226231575012},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43810826539993286},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.43558263778686523},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3534430265426636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3392583131790161},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32255059480667114},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1329236626625061}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951809167861938},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7548590302467346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661361217498779},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48342931270599365},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.47564244270324707},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.47328728437423706},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4729226231575012},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43810826539993286},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.43558263778686523},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3534430265426636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3392583131790161},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32255059480667114},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1329236626625061},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-58545-7_41","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-58545-7_41","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2007.12146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12146","pdf_url":"https://arxiv.org/pdf/2007.12146","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":"","raw_type":"text"},{"id":"mag:3045355015","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.12146.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.12146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.12146","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.12146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12146","pdf_url":"https://arxiv.org/pdf/2007.12146","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1566289585","https://openalex.org/W1933349210","https://openalex.org/W2008806374","https://openalex.org/W2012689760","https://openalex.org/W2053317383","https://openalex.org/W2058556535","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2493916176","https://openalex.org/W2519887557","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2787214294","https://openalex.org/W2809273748","https://openalex.org/W2884093133","https://openalex.org/W2890531016","https://openalex.org/W2899505139","https://openalex.org/W2945260553","https://openalex.org/W2946567085","https://openalex.org/W2946794439","https://openalex.org/W2949474740","https://openalex.org/W2954165458","https://openalex.org/W2963045354","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963925437","https://openalex.org/W2964121744","https://openalex.org/W2964302946","https://openalex.org/W2964308564","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2970550739","https://openalex.org/W2970565456","https://openalex.org/W2970608575","https://openalex.org/W2970971581","https://openalex.org/W2971274815","https://openalex.org/W2975501350","https://openalex.org/W2979382951","https://openalex.org/W2981851019","https://openalex.org/W2988326850","https://openalex.org/W2995460200","https://openalex.org/W2997591391","https://openalex.org/W2997753998","https://openalex.org/W2998356391","https://openalex.org/W3004268082","https://openalex.org/W3004349648","https://openalex.org/W3034336960","https://openalex.org/W3034727271","https://openalex.org/W3116651605","https://openalex.org/W6600804061","https://openalex.org/W6632575151","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3108319047","https://openalex.org/W3186371728","https://openalex.org/W3109142545","https://openalex.org/W3206904785","https://openalex.org/W2799122342","https://openalex.org/W3137627965","https://openalex.org/W3015092156","https://openalex.org/W837791456","https://openalex.org/W3092114159","https://openalex.org/W2994374529","https://openalex.org/W3000903387","https://openalex.org/W3138594634","https://openalex.org/W3082354956","https://openalex.org/W2944059049","https://openalex.org/W201688897","https://openalex.org/W2267737560","https://openalex.org/W2982392445","https://openalex.org/W2933801649","https://openalex.org/W1438166973","https://openalex.org/W2937322566"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}