{"id":"https://openalex.org/W2962968835","doi":"https://doi.org/10.1109/iccv.2017.323","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","display_name":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2962968835","doi":"https://doi.org/10.1109/iccv.2017.323","mag":"2962968835"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2017.323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","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/A5101990493","display_name":"Bo Dai","orcid":"https://orcid.org/0000-0003-0777-9232"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Dai","raw_affiliation_strings":["Department of Information Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070642269","display_name":"Sanja Fidler","orcid":"https://orcid.org/0000-0003-1040-3260"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sanja Fidler","raw_affiliation_strings":["University of Toronto","Vector Institute"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058557954","display_name":"Raquel Urtasun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123843","display_name":"Advanced Technologies Group (United States)","ror":"https://ror.org/0359sgh16","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123843"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Raquel Urtasun","raw_affiliation_strings":["Uber Advanced Technologies Group","University of Toronto"],"affiliations":[{"raw_affiliation_string":"Uber Advanced Technologies Group","institution_ids":["https://openalex.org/I4210123843"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["Department of Information Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101990493"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":20.4808,"has_fulltext":false,"cited_by_count":459,"citation_normalized_percentile":{"value":0.9952979,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2989","last_page":"2998"},"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":0.9900000095367432,"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":0.9872999787330627,"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/closed-captioning","display_name":"Closed captioning","score":0.8736642599105835},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8122321367263794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976046800613403},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7626367807388306},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6307271122932434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6005901098251343},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5599178075790405},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5533744692802429},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46424779295921326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4150616228580475}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8736642599105835},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8122321367263794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976046800613403},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7626367807388306},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6307271122932434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6005901098251343},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5599178075790405},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5533744692802429},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46424779295921326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4150616228580475},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv.2017.323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/352162","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/352162","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1706899115","https://openalex.org/W1780856595","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2125389028","https://openalex.org/W2133459682","https://openalex.org/W2149172860","https://openalex.org/W2154652894","https://openalex.org/W2155027007","https://openalex.org/W2185175083","https://openalex.org/W2302086703","https://openalex.org/W2405756170","https://openalex.org/W2430258811","https://openalex.org/W2506483933","https://openalex.org/W2549599535","https://openalex.org/W2558533273","https://openalex.org/W2575842049","https://openalex.org/W2607855566","https://openalex.org/W2963073614","https://openalex.org/W2963084599","https://openalex.org/W2963649796","https://openalex.org/W2964049455","https://openalex.org/W2964268978","https://openalex.org/W4320013936","https://openalex.org/W6630875275","https://openalex.org/W6637306801","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6682086108","https://openalex.org/W6682631176","https://openalex.org/W6683204974","https://openalex.org/W6713645886","https://openalex.org/W6725318829","https://openalex.org/W6728912905","https://openalex.org/W6729046916","https://openalex.org/W6736714560","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W172797710","https://openalex.org/W3005996785","https://openalex.org/W4386984417","https://openalex.org/W2476099471"],"abstract_inverted_index":{"Despite":[0],"the":[1,7,51,62,91,95,140,155,168,175],"substantial":[2],"progress":[3],"in":[4,33,45,192],"recent":[5],"years,":[6],"image":[8],"captioning":[9],"techniques":[10],"are":[11,27],"still":[12],"far":[13],"from":[14,163],"being":[15],"perfect.":[16],"Sentences":[17],"produced":[18],"by":[19,157],"existing":[20],"methods,":[21],"e.g.":[22,73],"those":[23],"based":[24,112],"on":[25,113,128,181,200],"RNNs,":[26],"often":[28],"overly":[29],"rigid":[30],"and":[31,75,97,130,196],"lacking":[32],"variability.":[34],"This":[35,56],"issue":[36],"is":[37,144,151],"related":[38],"to":[39,49,61,93,124,133,170],"a":[40,109,122,137,148,160],"learning":[41],"principle":[42,57],"widely":[43],"used":[44],"practice,":[46],"that":[47,146],"is,":[48],"maximize":[50],"likelihood":[52],"of":[53,103],"training":[54,147],"samples.":[55],"encourages":[58],"high":[59],"resemblance":[60],"\u201cground-truth\u201d":[63],"captions,":[64],"while":[65],"suppressing":[66],"other":[67,198],"reasonable":[68],"descriptions.":[69],"Conventional":[70],"evaluation":[71],"metrics,":[72],"BLEU":[74],"METEOR,":[76],"also":[77],"favor":[78],"such":[79],"restrictive":[80],"methods.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,107],"explore":[86],"an":[87,131],"alternative":[88],"approach,":[89],"with":[90],"aim":[92],"improve":[94],"naturalness":[96],"diversity":[98],"-":[99],"two":[100,182],"essential":[101],"properties":[102],"human":[104],"expression.":[105],"Specifically,":[106],"propose":[108],"new":[110],"framework":[111],"Conditional":[114],"Generative":[115],"Adversarial":[116],"Networks":[117],"(CGAN),":[118],"which":[119,166],"jointly":[120],"learns":[121],"generator":[123,150,169],"produce":[125],"descriptions":[126],"conditioned":[127],"images":[129],"evaluator":[132],"assess":[134],"how":[135],"well":[136],"description":[138],"fits":[139],"visual":[141],"content.":[142],"It":[143],"noteworthy":[145],"sequence":[149],"nontrivial.":[152],"We":[153,177],"overcome":[154],"difficulty":[156],"Policy":[158],"Gradient,":[159],"strategy":[161],"stemming":[162],"Reinforcement":[164],"Learning,":[165],"allows":[167],"receive":[171],"early":[172],"feedback":[173],"along":[174],"way.":[176],"tested":[178],"our":[179,193],"method":[180],"large":[183],"datasets,":[184],"where":[185],"it":[186],"performed":[187],"competitively":[188],"against":[189],"real":[190],"people":[191],"user":[194],"study":[195],"outperformed":[197],"methods":[199],"various":[201],"tasks.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":45},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":86},{"year":2019,"cited_by_count":97},{"year":2018,"cited_by_count":39},{"year":2017,"cited_by_count":3}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}