{"id":"https://openalex.org/W2803525166","doi":"https://doi.org/10.1609/aaai.v33i01.33018142","title":"Improving Image Captioning with Conditional Generative Adversarial Nets","display_name":"Improving Image Captioning with Conditional Generative Adversarial Nets","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2803525166","doi":"https://doi.org/10.1609/aaai.v33i01.33018142","mag":"2803525166"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018142","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018142","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33018142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Mu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanpeng Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanpeng Xiao","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexiong Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexiong Ye","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liesi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liesi Wu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qi Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Ju","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":5.2618,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.96027875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"8142","last_page":"8150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9818999767303467,"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":0.9818999767303467,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004999999888241291,"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":0.0013000000035390258,"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":0.9918000102043152},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8091999888420105},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.701200008392334},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42890000343322754},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.428600013256073},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9918000102043152},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8091999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678999900817871},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.701200008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609000027179718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018142","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018142","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1805.07112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07112","pdf_url":"https://arxiv.org/pdf/1805.07112","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":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/4823","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4823","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4823/4696","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018142","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018142","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2155027007","https://openalex.org/W2523469089","https://openalex.org/W2560313346","https://openalex.org/W2575842049","https://openalex.org/W2597985671","https://openalex.org/W2604178507","https://openalex.org/W2607151106","https://openalex.org/W2745461083","https://openalex.org/W2949376505","https://openalex.org/W2950304420","https://openalex.org/W6639102338","https://openalex.org/W6639657675","https://openalex.org/W6677916085","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6729624334","https://openalex.org/W6753850902","https://openalex.org/W6898505805"],"related_works":[],"abstract_inverted_index":{"In":[0,120],"this":[1],"paper,":[2],"we":[3,32,88,105],"propose":[4],"a":[5,98],"novel":[6],"conditional-generativeadversarial-nets-based":[7],"image":[8,84,117,131],"captioning":[9,85,118,132],"framework":[10,86],"as":[11,129],"an":[12],"extension":[13],"of":[14,56,101],"traditional":[15],"reinforcement-learning":[16],"(RL)-based":[17],"encoder-decoder":[18],"architecture.":[19],"To":[20],"deal":[21],"with":[22],"the":[23,91,122],"inconsistent":[24],"evaluation":[25,112],"problem":[26],"among":[27],"different":[28,115],"objective":[29,130],"language":[30,111],"metrics,":[31],"are":[33,63],"motivated":[34],"to":[35,40],"design":[36],"some":[37],"\u201cdiscriminator\u201d":[38],"networks":[39],"automatically":[41],"and":[42,60,87],"progressively":[43],"determine":[44],"whether":[45],"generated":[46],"caption":[47],"is":[48,74,96],"human":[49],"described":[50],"or":[51],"machine":[52],"generated.":[53],"Two":[54],"kinds":[55],"discriminator":[57],"architectures":[58],"(CNN":[59],"RNNbased":[61],"structures)":[62],"introduced":[64],"since":[65],"each":[66],"has":[67],"its":[68],"own":[69],"advantages.":[70],"The":[71],"proposed":[72],"algorithm":[73],"generic":[75],"so":[76],"that":[77,90],"it":[78],"can":[79,125],"enhance":[80],"any":[81],"existing":[82],"RL-based":[83],"show":[89,106],"conventional":[92],"RL":[93],"training":[94],"method":[95],"just":[97],"special":[99],"case":[100],"our":[102],"approach.":[103],"Empirically,":[104],"consistent":[107],"improvements":[108],"over":[109],"all":[110],"metrics":[113],"for":[114],"state-of-the-art":[116],"models.":[119],"addition,":[121],"well-trained":[123],"discriminators":[124],"also":[126],"be":[127],"viewed":[128],"evaluators.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2018-06-01T00:00:00"}