{"id":"https://openalex.org/W2891999386","doi":"https://doi.org/10.18653/v1/d18-1281","title":"Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation","display_name":"Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891999386","doi":"https://doi.org/10.18653/v1/d18-1281","mag":"2891999386"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1281","pdf_url":"https://www.aclweb.org/anthology/D18-1281.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1281.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070532113","display_name":"Ryota Hinami","orcid":"https://orcid.org/0000-0003-1542-2612"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryota Hinami","raw_affiliation_strings":["National Institute of Infomatics","The University of Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Infomatics","institution_ids":[]},{"raw_affiliation_string":"The University of Tokyo,","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743927","display_name":"Shin\u2019ichi Satoh","orcid":"https://orcid.org/0000-0001-6995-6447"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin\u2019ichi Satoh","raw_affiliation_strings":["National Institute of Infomatics","The University of Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Infomatics","institution_ids":[]},{"raw_affiliation_string":"The University of Tokyo,","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070532113"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2605","last_page":"2615"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165689706802368},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7595642805099487},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7144533395767212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6612709760665894},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6409859657287598},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5404165387153625},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5130959749221802},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49398595094680786},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.48334071040153503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4700640141963959},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.46829360723495483},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3885743021965027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3861802816390991},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23260760307312012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165689706802368},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7595642805099487},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7144533395767212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6612709760665894},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6409859657287598},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5404165387153625},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5130959749221802},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49398595094680786},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.48334071040153503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4700640141963959},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.46829360723495483},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3885743021965027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3861802816390991},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23260760307312012},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1281","pdf_url":"https://www.aclweb.org/anthology/D18-1281.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1281","pdf_url":"https://www.aclweb.org/anthology/D18-1281.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1125644438","display_name":"\u5927\u898f\u6a21\u6620\u50cf\u4e2d\u306e\u7269\u4f53\u691c\u7d22\u6280\u8853\u306b\u95a2\u3059\u308b\u7814\u7a76\u3068\u305d\u306e\u653e\u9001\u6620\u50cf\u30a2\u30fc\u30ab\u30a4\u30d6\u3078\u306e\u5fdc\u7528","funder_award_id":"17J08378","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1875132913","display_name":null,"funder_award_id":"JPMJCR1686","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891999386.pdf","grobid_xml":"https://content.openalex.org/works/W2891999386.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W870084106","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1825604117","https://openalex.org/W1861492603","https://openalex.org/W1931795219","https://openalex.org/W1969198793","https://openalex.org/W2056968687","https://openalex.org/W2065296697","https://openalex.org/W2081580037","https://openalex.org/W2084430102","https://openalex.org/W2102605133","https://openalex.org/W2124509324","https://openalex.org/W2126967273","https://openalex.org/W2144960104","https://openalex.org/W2153579005","https://openalex.org/W2168356304","https://openalex.org/W2174726731","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2414711238","https://openalex.org/W2520141964","https://openalex.org/W2520824046","https://openalex.org/W2568262903","https://openalex.org/W2570343428","https://openalex.org/W2606746036","https://openalex.org/W2613718673","https://openalex.org/W2949474740","https://openalex.org/W2953133772","https://openalex.org/W2962714319","https://openalex.org/W2962811161","https://openalex.org/W2962835968","https://openalex.org/W2963109634","https://openalex.org/W2963383024","https://openalex.org/W2963389687","https://openalex.org/W2963446957","https://openalex.org/W2963516811","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W2963914122","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W3098232790","https://openalex.org/W4214784241","https://openalex.org/W4294170691","https://openalex.org/W4297813007","https://openalex.org/W4386506836","https://openalex.org/W6818233367"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2147874738","https://openalex.org/W2036058638","https://openalex.org/W2513891871"],"abstract_inverted_index":{"Thanks":[0],"to":[1,90,117,126],"the":[2,13,22,55,64,95,127,131,138],"success":[3],"of":[4,12,40,57,86,137],"object":[5,25,59,66,101],"detection":[6],"technology,":[7],"we":[8,53,110],"can":[9,31,143],"retrieve":[10,144],"objects":[11,147],"specified":[14,68,148],"classes":[15],"even":[16],"from":[17,153],"huge":[18],"image":[19],"collections.":[20],"However,":[21],"current":[23],"state-of-the-art":[24],"detectors":[26],"(such":[27],"as":[28],"Faster":[29,87],"R-CNN)":[30],"only":[32,158],"handle":[33],"pre-specified":[34],"classes.":[35],"In":[36,50],"addition,":[37],"large":[38],"amounts":[39],"positive":[41],"and":[42,61,103,129,145],"negative":[43,113,120],"visual":[44],"samples":[45,121],"are":[46,123],"required":[47],"for":[48,107],"training.":[49],"this":[51],"paper,":[52],"address":[54],"problem":[56],"open-vocabulary":[58,91],"retrieval":[60],"localization,":[62],"where":[63],"target":[65],"is":[67],"by":[69,93,149],"a":[70,74,83,150],"textual":[71,151],"query":[72,128,152],"(e.g.,":[73],"word":[75],"or":[76],"phrase).":[77],"We":[78],"first":[79],"propose":[80,112],"Query-Adaptive":[81],"R-CNN,":[82],"simple":[84],"extension":[85],"R-CNN":[88],"adapted":[89],"queries,":[92],"transforming":[94],"text":[96],"embedding":[97],"vector":[98],"into":[99],"an":[100],"classifier":[102],"localization":[104],"regressor.":[105],"Then,":[106],"discriminative":[108],"training,":[109],"then":[111],"phrase":[114],"augmentation":[115],"(NPA)":[116],"mine":[118],"hard":[119],"which":[122],"visually":[124],"similar":[125],"at":[130],"same":[132],"time":[133],"semantically":[134],"mutually":[135],"exclusive":[136],"query.":[139],"The":[140],"proposed":[141],"method":[142],"localize":[146],"one":[154],"million":[155],"images":[156],"in":[157],"0.5":[159],"seconds":[160],"with":[161],"high":[162],"precision.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}