{"id":"https://openalex.org/W3091232662","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207417","title":"Zero-Shot Object Detection with Textual Descriptions Using Convolutional Neural Networks","display_name":"Zero-Shot Object Detection with Textual Descriptions Using Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091232662","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207417","mag":"3091232662"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.lib.uts.edu.au/bitstream/10453/140298/2/PID6439365.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100612751","display_name":"Licheng Zhang","orcid":"https://orcid.org/0000-0001-8090-4883"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["AU","CN"],"is_corresponding":true,"raw_author_name":"Licheng Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology","School of Computer Science, University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076107706","display_name":"Xianzhi Wang","orcid":"https://orcid.org/0000-0001-9582-3445"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xianzhi Wang","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063285882","display_name":"Feng Zheng","orcid":"https://orcid.org/0000-0002-1701-9141"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zheng","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100612751"],"corresponding_institution_ids":["https://openalex.org/I114017466","https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.1963,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.50814943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9972000122070312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9952999949455261,"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":0.8487426042556763},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7706739902496338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7026464343070984},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6934494376182556},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6297516822814941},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5687536001205444},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5200493335723877},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4689701795578003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4549044072628021},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44594067335128784},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4300304651260376},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42701610922813416},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.42171138525009155},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.391866534948349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3873569071292877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487426042556763},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7706739902496338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7026464343070984},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6934494376182556},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6297516822814941},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5687536001205444},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5200493335723877},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4689701795578003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4549044072628021},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44594067335128784},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4300304651260376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42701610922813416},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.42171138525009155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.391866534948349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3873569071292877},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/140298","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/140298","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/140298/2/PID6439365.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/140298","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/140298","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/140298/2/PID6439365.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3091232662.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W841113906","https://openalex.org/W1536680647","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2145215286","https://openalex.org/W2170240176","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2274287116","https://openalex.org/W2277195237","https://openalex.org/W2289084343","https://openalex.org/W2413904250","https://openalex.org/W2552383788","https://openalex.org/W2609698233","https://openalex.org/W2748618181","https://openalex.org/W2772366472","https://openalex.org/W2905535961","https://openalex.org/W2910453440","https://openalex.org/W2963012544","https://openalex.org/W2963150697","https://openalex.org/W2963486920","https://openalex.org/W2963516811","https://openalex.org/W2963545832","https://openalex.org/W2963777148","https://openalex.org/W2963854535","https://openalex.org/W2963936013","https://openalex.org/W2963960318","https://openalex.org/W2964350391","https://openalex.org/W4295332732","https://openalex.org/W6620707391","https://openalex.org/W6623333368","https://openalex.org/W6639102338","https://openalex.org/W6675026286","https://openalex.org/W6685053522","https://openalex.org/W6687483927","https://openalex.org/W6694260854","https://openalex.org/W6694395031","https://openalex.org/W6715835459","https://openalex.org/W6729840497","https://openalex.org/W6746524570","https://openalex.org/W6749149297","https://openalex.org/W6750462345","https://openalex.org/W6752354721"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3093612317","https://openalex.org/W3038672259","https://openalex.org/W2801801420","https://openalex.org/W2296151615","https://openalex.org/W3090693157","https://openalex.org/W2059299633","https://openalex.org/W2756241593","https://openalex.org/W4300122426","https://openalex.org/W2796497263"],"abstract_inverted_index":{"Zero-shot":[0],"object":[1,121,168,184],"detection":[2,68,101],"aims":[3],"to":[4,24,55,81,135,146,156,181,203],"detect":[5],"and":[6,29,65,115,132,139,143,155,174,186],"recognize":[7],"objects":[8,78,152,161],"unobserved":[9],"in":[10,40,153],"training":[11,62],"samples":[12],"from":[13,171],"images.":[14],"Previous":[15],"studies":[16],"generally":[17],"utilized":[18],"concept":[19],"names":[20,76],"or":[21],"textual":[22,41,48,71,172],"descriptions":[23,42,49,72,118,173],"build":[25],"relationships":[26],"between":[27],"seen":[28],"unseen":[30,95],"classes.":[31],"However,":[32],"these":[33],"works":[34],"rarely":[35],"exploited":[36],"the":[37,45,63,67,75,91,100,148,197],"valuable":[38,52],"information":[39,53,59],"for":[43,119],"optimizing":[44],"network.":[46],"Actually,":[47],"contain":[50,74,151],"much":[51],"related":[54],"categories.":[56],"Exploiting":[57],"this":[58,86,104],"can":[60,89,98],"help":[61],"network":[64,130,187],"improve":[66,99],"performance.":[69],"Besides,":[70,163],"usually":[73],"of":[77,93,200],"that":[79,111,150],"need":[80],"be":[82],"detected.":[83],"By":[84],"using":[85],"character,":[87],"we":[88,106,125,164],"narrow":[90],"scope":[92],"candidate":[94],"categories,":[96],"thus":[97],"accuracy.":[102],"In":[103,123],"regard,":[105],"propose":[107],"a":[108],"novel":[109],"framework":[110],"incorporates":[112],"both":[113],"images":[114,154],"their":[116],"text":[117,127,137],"zero-shot":[120],"detection.":[122],"particular,":[124],"employ":[126],"convolutional":[128],"neural":[129],"(CNN)":[131],"Faster":[133],"R-CNN":[134],"extract":[136],"features":[138,141],"image":[140],"respectively,":[142],"combine":[144],"them":[145],"optimize":[147],"regions":[149],"classify":[157],"those":[158],"newly":[159],"detected":[160],"simultaneously.":[162],"try":[165],"extracting":[166],"potential":[167],"labels":[169],"directly":[170],"introducing":[175],"online":[176],"hard":[177],"example":[178],"mining":[179],"(OHEM)":[180],"assist":[182],"with":[183],"classification":[185],"optimization.":[188],"Our":[189],"extensive":[190],"experiments":[191],"on":[192],"two":[193],"public":[194],"datasets":[195],"demonstrate":[196],"superior":[198],"performance":[199],"our":[201],"approach":[202],"state-of-the-art":[204],"methods.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}