{"id":"https://openalex.org/W2902440562","doi":"https://doi.org/10.1109/icpr.2018.8545049","title":"Image Captioning using Adversarial Networks and Reinforcement Learning","display_name":"Image Captioning using Adversarial Networks and Reinforcement Learning","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2902440562","doi":"https://doi.org/10.1109/icpr.2018.8545049","mag":"2902440562"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8545049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","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/A5007039694","display_name":"Shiyang Yan","orcid":"https://orcid.org/0000-0003-1411-5952"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shiyang Yan","raw_affiliation_strings":["Department of Electrical Engineering and Electronics, University of Liverpool"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Electronics, University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fangyu Wu","raw_affiliation_strings":["Department of Electrical Engineering and Electronics, University of Liverpool"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Electronics, University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003757015","display_name":"Jeremy S. Smith","orcid":"https://orcid.org/0000-0002-0212-2365"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeremy S. Smith","raw_affiliation_strings":["Department of Electrical Engineering and Electronics, University of Liverpool"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Electronics, University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110074987","display_name":"Wenjin Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Lu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Xi'an Jiaotong-Iiverpool University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Xi'an Jiaotong-Iiverpool University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101991543","display_name":"Bailing Zhang","orcid":"https://orcid.org/0000-0001-5762-5763"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bailing Zhang","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Xi'an Jiaotong-Iiverpool University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Xi'an Jiaotong-Iiverpool University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007039694"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":null,"apc_paid":null,"fwci":1.149,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.84057786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"248","last_page":"253"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976999759674072,"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":0.9962999820709229,"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":0.9616460800170898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221421241760254},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6770049333572388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6523646712303162},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5939476490020752},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5163480043411255},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5019214153289795},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47531062364578247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43374747037887573},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4246487021446228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3456355035305023}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9616460800170898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221421241760254},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6770049333572388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6523646712303162},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5939476490020752},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5163480043411255},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5019214153289795},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47531062364578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43374747037887573},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4246487021446228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3456355035305023},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2018.8545049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2122180654","https://openalex.org/W2123301721","https://openalex.org/W2125389028","https://openalex.org/W2132083787","https://openalex.org/W2133564696","https://openalex.org/W2155027007","https://openalex.org/W2155893237","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2271840356","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2607151106","https://openalex.org/W2919115771","https://openalex.org/W2962835968","https://openalex.org/W2962968835","https://openalex.org/W2964121744","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W4214717370","https://openalex.org/W4320013936","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6677969093","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6683204974","https://openalex.org/W6727862155","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,148,170],"a":[3,45,102,118,142],"significant":[4,46],"task":[5,40],"in":[6,49,62],"artificial":[7],"intelligence":[8],"which":[9,79],"connects":[10],"computer":[11],"vision":[12],"and":[13,88],"natural":[14],"language":[15,106,140],"processing.":[16],"With":[17],"the":[18,24,35,39,50,53,63,82,110,113,125,128,133,137,153,157,164],"rapid":[19],"development":[20],"of":[21,34,41,57,86,112,139,163],"deep":[22],"learning,":[23],"sequence":[25,27,64],"to":[26,101,109,123,131],"model":[28],"with":[29],"attention,":[30],"has":[31],"become":[32],"one":[33],"main":[36],"approaches":[37],"for":[38,76,81,127],"image":[42,77],"captioning.":[43],"Nevertheless,":[44],"issue":[47],"exists":[48],"current":[51],"framework:":[52],"exposure":[54,83],"bias":[55,84],"problem":[56,85],"Maximum":[58],"Likelihood":[59],"Estimation":[60],"(MLE)":[61],"model.":[65,166],"To":[66],"address":[67],"this":[68],"problem,":[69],"we":[70,116],"use":[71,117],"generative":[72],"adversarial":[73],"networks":[74],"(GANs)":[75],"captioning,":[78],"compensates":[80],"MLE":[87],"also":[89,171],"can":[90],"generate":[91],"more":[92],"realistic":[93],"captions.":[94],"GANs,":[95],"however,":[96],"cannot":[97],"be":[98],"directly":[99],"applied":[100],"discrete":[103],"task,":[104],"like":[105],"processing,":[107],"due":[108],"discontinuity":[111],"data.":[114],"Hence,":[115],"reinforcement":[119],"learning":[120],"(RL)":[121],"technique":[122],"estimate":[124],"gradients":[126],"network.":[129],"Also,":[130],"obtain":[132],"intermediate":[134],"rewards":[135],"during":[136],"process":[138],"generation,":[141],"Monte":[143],"Carlo":[144],"roll-out":[145],"sampling":[146],"method":[147],"utilized.":[149],"Experimental":[150],"results":[151],"on":[152],"COCO":[154],"dataset":[155],"validate":[156],"improved":[158],"effect":[159],"from":[160],"each":[161],"ingredient":[162],"proposed":[165],"The":[167],"overall":[168],"effectiveness":[169],"evaluated.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}