{"id":"https://openalex.org/W2967593235","doi":"https://doi.org/10.18653/v1/d19-1219","title":"Fusion of Detected Objects in Text for Visual Question Answering","display_name":"Fusion of Detected Objects in Text for Visual Question Answering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2967593235","doi":"https://doi.org/10.18653/v1/d19-1219","mag":"2967593235"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-1219","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1219","pdf_url":"https://www.aclweb.org/anthology/D19-1219.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-1219.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065685274","display_name":"Chris Alberti","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Alberti","raw_affiliation_strings":["Google Research","Alphabet Inc"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Alphabet Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007888987","display_name":"Jeffrey Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Ling","raw_affiliation_strings":["Google Research","Alphabet Inc"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Alphabet Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111220663","display_name":"Michael Collins","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Collins","raw_affiliation_strings":["Google Research","Alphabet Inc"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Alphabet Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020881468","display_name":"David Reitter","orcid":"https://orcid.org/0000-0002-7887-8257"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Reitter","raw_affiliation_strings":["Google Research","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065685274"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.27543029,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9517172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2131","last_page":"2140"},"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":0.9991000294685364,"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":0.9966999888420105,"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":0.7839183807373047},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6571532487869263},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5942836403846741},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5739969611167908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5520192384719849},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5445916056632996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5046058893203735},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.495730996131897},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4939044117927551},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.47088155150413513},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4480392336845398},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4304931163787842},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.350283145904541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839183807373047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6571532487869263},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5942836403846741},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5739969611167908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5520192384719849},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5445916056632996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5046058893203735},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.495730996131897},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4939044117927551},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.47088155150413513},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4480392336845398},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4304931163787842},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.350283145904541},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-1219","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1219","pdf_url":"https://www.aclweb.org/anthology/D19-1219.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.05054","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.05054","pdf_url":"https://arxiv.org/pdf/1908.05054","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:2967593235","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1908.05054","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.1908.05054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.05054","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":"doi:10.18653/v1/d19-1219","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1219","pdf_url":"https://www.aclweb.org/anthology/D19-1219.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2967593235.pdf","grobid_xml":"https://content.openalex.org/works/W2967593235.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2112184938","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2302255633","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2882319491","https://openalex.org/W2886641317","https://openalex.org/W2901894078","https://openalex.org/W2931316642","https://openalex.org/W2938082352","https://openalex.org/W2949554544","https://openalex.org/W2950104027","https://openalex.org/W2950761309","https://openalex.org/W2953388933","https://openalex.org/W2962779279","https://openalex.org/W2963115613","https://openalex.org/W2963223524","https://openalex.org/W2963264012","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963890019","https://openalex.org/W2968124245","https://openalex.org/W2968880719","https://openalex.org/W2969876226","https://openalex.org/W2970608575","https://openalex.org/W2979401726"],"related_works":["https://openalex.org/W2968124245","https://openalex.org/W2970608575","https://openalex.org/W2963341956","https://openalex.org/W2745461083","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2963403868","https://openalex.org/W2277195237","https://openalex.org/W2995460200","https://openalex.org/W2968880719","https://openalex.org/W2963115613","https://openalex.org/W2975501350","https://openalex.org/W2886641317","https://openalex.org/W2560730294","https://openalex.org/W3020257313","https://openalex.org/W2970231061","https://openalex.org/W2965373594","https://openalex.org/W1861492603","https://openalex.org/W2981851019","https://openalex.org/W1889081078"],"abstract_inverted_index":{"To":[0],"advance":[1],"models":[2,119],"of":[3,37,84,97,110,117],"multimodal":[4],"context,":[5],"we":[6],"introduce":[7],"a":[8,41,57,61],"simple":[9],"yet":[10],"powerful":[11],"neural":[12],"architecture":[13],"for":[14],"data":[15],"that":[16,93],"combines":[17],"vision":[18],"and":[19,72],"natural":[20],"language.":[21],"The":[22],"\"Bounding":[23],"Boxes":[24],"in":[25,40,65],"Text":[26],"Transformer\"":[27],"(B2T2)":[28],"also":[29],"leverages":[30],"referential":[31],"information":[32],"binding":[33],"words":[34],"to":[35,69,77,107],"portions":[36],"the":[38,50,74,80,94,98,102,108,111],"image":[39],"single":[42],"unified":[43],"architecture.":[44,113],"B2T2":[45],"is":[46,105,120],"highly":[47],"effective":[48],"on":[49,79],"Visual":[51],"Commonsense":[52],"Reasoning":[53],"benchmark":[54],"(https://visualcommonsense.com),":[55],"achieving":[56],"new":[58,112],"state-of-the-art":[59],"with":[60],"25%":[62],"relative":[63],"reduction":[64],"error":[66],"rate":[67],"compared":[68],"published":[70],"baselines":[71],"obtaining":[73],"best":[75],"performance":[76],"date":[78],"public":[81],"leaderboard":[82],"(as":[83],"May":[85],"22,":[86],"2019).":[87],"A":[88,114],"detailed":[89],"ablation":[90],"analysis":[91,104],"shows":[92],"early":[95],"integration":[96],"visual":[99],"features":[100],"into":[101],"text":[103],"key":[106],"effectiveness":[109],"reference":[115],"implementation":[116],"our":[118],"provided":[121],"(https://github.com/google-research/language/tree/master/language/question_answering/b2t2).":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":5}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}