{"id":"https://openalex.org/W2606746036","doi":"https://doi.org/10.1109/cvpr.2017.122","title":"Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries","display_name":"Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2606746036","doi":"https://doi.org/10.1109/cvpr.2017.122","mag":"2606746036"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2017.122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451844","display_name":"Yuting Zhang","orcid":"https://orcid.org/0009-0005-8698-6142"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuting Zhang","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052478712","display_name":"Luyao Yuan","orcid":"https://orcid.org/0000-0001-6624-1227"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luyao Yuan","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677851","display_name":"Yijie Guo","orcid":"https://orcid.org/0000-0002-4949-2048"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijie Guo","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027441055","display_name":"Zhiyuan He","orcid":"https://orcid.org/0000-0002-8919-9997"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyuan He","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103128469","display_name":"Ian Huang","orcid":"https://orcid.org/0009-0000-8426-7543"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-An Huang","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108652283","display_name":"Honglak Lee","orcid":"https://orcid.org/0000-0002-4109-327X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honglak Lee","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100451844"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":2.8657,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.94706754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1090","last_page":"1099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922000169754028,"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/discriminative-model","display_name":"Discriminative model","score":0.9285268187522888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337111473083496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7293114066123962},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6647028923034668},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5767416954040527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5231591463088989},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4525373578071594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4388276934623718},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.43694862723350525},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4317992031574249},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41297584772109985},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33470624685287476}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9285268187522888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337111473083496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7293114066123962},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6647028923034668},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5767416954040527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5231591463088989},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4525373578071594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4388276934623718},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.43694862723350525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4317992031574249},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41297584772109985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33470624685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2017.122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W639708223","https://openalex.org/W1486649854","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1810943226","https://openalex.org/W1811254738","https://openalex.org/W1832693441","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1960182310","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2088049833","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2120615054","https://openalex.org/W2123099218","https://openalex.org/W2123301721","https://openalex.org/W2142192571","https://openalex.org/W2147800946","https://openalex.org/W2150066425","https://openalex.org/W2155893237","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2168356304","https://openalex.org/W2170240176","https://openalex.org/W2173180041","https://openalex.org/W2179352600","https://openalex.org/W2183182206","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2302548814","https://openalex.org/W2398118205","https://openalex.org/W2405756170","https://openalex.org/W2407521645","https://openalex.org/W2489434015","https://openalex.org/W2508429489","https://openalex.org/W2613718673","https://openalex.org/W2950094539","https://openalex.org/W2950800384","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2963012544","https://openalex.org/W2963037989","https://openalex.org/W2963109634","https://openalex.org/W2963542991","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W2964284374","https://openalex.org/W3098232790","https://openalex.org/W4239072543","https://openalex.org/W6600313631","https://openalex.org/W6607974698","https://openalex.org/W6620707391","https://openalex.org/W6629028937","https://openalex.org/W6629368666","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639204139","https://openalex.org/W6676297131","https://openalex.org/W6676338569","https://openalex.org/W6678262379","https://openalex.org/W6678415854","https://openalex.org/W6684191040","https://openalex.org/W6685053522","https://openalex.org/W6691231616","https://openalex.org/W6697921835","https://openalex.org/W6713645886","https://openalex.org/W6714138976","https://openalex.org/W6723035356","https://openalex.org/W6724784328","https://openalex.org/W6785355775"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W1487808658","https://openalex.org/W2129933262","https://openalex.org/W2005234362","https://openalex.org/W2162970382","https://openalex.org/W1997235926"],"abstract_inverted_index":{"Associating":[0],"image":[1,96],"regions":[2,97],"with":[3,71,98],"text":[4,87,99],"queries":[5],"has":[6],"been":[7,25],"recently":[8],"explored":[9],"as":[10],"a":[11,53,58,69,90],"new":[12],"way":[13],"to":[14],"bridge":[15],"visual":[16,48,142],"and":[17,93,103,127],"linguistic":[18],"representations.":[19],"A":[20],"few":[21],"pioneering":[22],"approaches":[23],"have":[24],"proposed":[26,114],"based":[27],"on":[28,83,107,124,130],"recurrent":[29],"neural":[30,61],"language":[31],"models":[32],"trained":[33,67],"generatively":[34],"(e.g.,":[35],"generating":[36],"captions),":[37],"but":[38],"achieving":[39],"somewhat":[40],"limited":[41],"localization":[42,82,123],"accuracy.":[43],"To":[44],"better":[45,81],"address":[46],"natural-language-based":[47],"entity":[49],"localization,":[50],"we":[51,134],"propose":[52],"discriminative":[54,59],"approach.":[55],"We":[56,133],"formulate":[57],"bimodal":[60],"network":[62],"(DBNet),":[63],"which":[64],"can":[65],"be":[66],"by":[68],"classifier":[70],"extensive":[72],"use":[73],"of":[74],"negative":[75,104],"samples.":[76],"Our":[77],"training":[78],"objective":[79],"encourages":[80],"single":[84,125],"images,":[85],"incorporates":[86],"phrases":[88,100],"in":[89],"broad":[91],"range,":[92],"properly":[94],"pairs":[95],"into":[101],"positive":[102],"examples.":[105],"Experiments":[106],"the":[108,113],"Visual":[109],"Genome":[110],"dataset":[111],"demonstrate":[112],"DBNet":[115],"significantly":[116],"outperforms":[117],"previous":[118],"state-of-the-art":[119],"methods":[120],"both":[121],"for":[122,128,140],"images":[126],"detection":[129],"multiple":[131],"images.":[132],"also":[135],"establish":[136],"an":[137],"evaluation":[138],"protocol":[139],"natural-language":[141],"detection.":[143],"Code":[144],"is":[145],"available":[146],"at:":[147],"http://ytzhang.net/projects/dbnet.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-23T06:14:38.165362","created_date":"2025-10-10T00:00:00"}