{"id":"https://openalex.org/W4392982156","doi":"https://doi.org/10.1109/cvmi59935.2023.10464514","title":"Image Captioning with Reinforcement Learning","display_name":"Image Captioning with Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-10","ids":{"openalex":"https://openalex.org/W4392982156","doi":"https://doi.org/10.1109/cvmi59935.2023.10464514"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi59935.2023.10464514","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvmi59935.2023.10464514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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/A5100998743","display_name":"Anand Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I9747756","display_name":"Atal Bihari Vajpayee Indian Institute of Information Technology and Management","ror":"https://ror.org/008b3ap06","country_code":"IN","type":"education","lineage":["https://openalex.org/I9747756"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anand Verma","raw_affiliation_strings":["ABV-IIITM Gwalior,Department of Information Technology,Madhya Pradesh,India,474015"],"affiliations":[{"raw_affiliation_string":"ABV-IIITM Gwalior,Department of Information Technology,Madhya Pradesh,India,474015","institution_ids":["https://openalex.org/I9747756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101970545","display_name":"Saurabh Agarwal","orcid":"https://orcid.org/0009-0003-1379-0371"},"institutions":[{"id":"https://openalex.org/I9747756","display_name":"Atal Bihari Vajpayee Indian Institute of Information Technology and Management","ror":"https://ror.org/008b3ap06","country_code":"IN","type":"education","lineage":["https://openalex.org/I9747756"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saurabh Agarwal","raw_affiliation_strings":["ABV-Indian Institute of Information Technology and Management,Multimedia and Information Security Research Group,Department of Computer Science and Engineering,Gwalior,India,474015"],"affiliations":[{"raw_affiliation_string":"ABV-Indian Institute of Information Technology and Management,Multimedia and Information Security Research Group,Department of Computer Science and Engineering,Gwalior,India,474015","institution_ids":["https://openalex.org/I9747756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055521846","display_name":"K. V. Arya","orcid":"https://orcid.org/0000-0001-7117-1745"},"institutions":[{"id":"https://openalex.org/I9747756","display_name":"Atal Bihari Vajpayee Indian Institute of Information Technology and Management","ror":"https://ror.org/008b3ap06","country_code":"IN","type":"education","lineage":["https://openalex.org/I9747756"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K.V. Arya","raw_affiliation_strings":["ABV-Indian Institute of Information Technology and Management,Multimedia and Information Security Research Group,Department of Computer Science and Engineering,Gwalior,India,474015"],"affiliations":[{"raw_affiliation_string":"ABV-Indian Institute of Information Technology and Management,Multimedia and Information Security Research Group,Department of Computer Science and Engineering,Gwalior,India,474015","institution_ids":["https://openalex.org/I9747756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049181212","display_name":"Iv\u00e1n Petrlik","orcid":"https://orcid.org/0000-0002-1201-2143"},"institutions":[{"id":"https://openalex.org/I115253235","display_name":"Federico Villarreal National University","ror":"https://ror.org/015wdp703","country_code":"PE","type":"education","lineage":["https://openalex.org/I115253235"]}],"countries":["PE"],"is_corresponding":false,"raw_author_name":"Ivan Petrlik","raw_affiliation_strings":["National University Federico Villarreal,Faculty of Industrial and Systems Engineering,Lima,Peru","Faculty of Industrial and Systems Engineering, National University Federico Villarreal, Lima, Peru"],"affiliations":[{"raw_affiliation_string":"National University Federico Villarreal,Faculty of Industrial and Systems Engineering,Lima,Peru","institution_ids":["https://openalex.org/I115253235"]},{"raw_affiliation_string":"Faculty of Industrial and Systems Engineering, National University Federico Villarreal, Lima, Peru","institution_ids":["https://openalex.org/I115253235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108910140","display_name":"Roberto Esparza","orcid":null},"institutions":[{"id":"https://openalex.org/I115253235","display_name":"Federico Villarreal National University","ror":"https://ror.org/015wdp703","country_code":"PE","type":"education","lineage":["https://openalex.org/I115253235"]}],"countries":["PE"],"is_corresponding":false,"raw_author_name":"Roberto Esparza","raw_affiliation_strings":["National University Federico Villarreal,Faculty of Industrial and Systems Engineering,Lima,Peru","Faculty of Industrial and Systems Engineering, National University Federico Villarreal, Lima, Peru"],"affiliations":[{"raw_affiliation_string":"National University Federico Villarreal,Faculty of Industrial and Systems Engineering,Lima,Peru","institution_ids":["https://openalex.org/I115253235"]},{"raw_affiliation_string":"Faculty of Industrial and Systems Engineering, National University Federico Villarreal, Lima, Peru","institution_ids":["https://openalex.org/I115253235"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039927860","display_name":"Ciro Rodr\u00edguez","orcid":"https://orcid.org/0000-0003-2112-1349"},"institutions":[{"id":"https://openalex.org/I192513696","display_name":"National University of San Marcos","ror":"https://ror.org/006vs7897","country_code":"PE","type":"education","lineage":["https://openalex.org/I192513696"]}],"countries":["PE"],"is_corresponding":false,"raw_author_name":"Ciro Rodriguez","raw_affiliation_strings":["National University Mayor de San Marcos,Faculty of Systems Engineering and Informatics","Faculty of Systems Engineering and Informatics, National University Mayor de San Marcos"],"affiliations":[{"raw_affiliation_string":"National University Mayor de San Marcos,Faculty of Systems Engineering and Informatics","institution_ids":["https://openalex.org/I192513696"]},{"raw_affiliation_string":"Faculty of Systems Engineering and Informatics, National University Mayor de San Marcos","institution_ids":["https://openalex.org/I192513696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100998743"],"corresponding_institution_ids":["https://openalex.org/I9747756"],"apc_list":null,"apc_paid":null,"fwci":0.1228,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46981325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"16","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9776999950408936,"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":0.9714000225067139,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9649826288223267},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7319130897521973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722346305847168},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5347957015037537},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.450447678565979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4498502314090729},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34065717458724976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11530980467796326},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.062477678060531616}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9649826288223267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7319130897521973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722346305847168},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5347957015037537},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.450447678565979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4498502314090729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34065717458724976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11530980467796326},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.062477678060531616}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi59935.2023.10464514","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvmi59935.2023.10464514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2109586012","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2800782462","https://openalex.org/W2949376505","https://openalex.org/W2963084599","https://openalex.org/W2965846473","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W2998988444","https://openalex.org/W3034733309","https://openalex.org/W3035284526","https://openalex.org/W3044889983","https://openalex.org/W3091588028","https://openalex.org/W3102371147","https://openalex.org/W3103022576","https://openalex.org/W3134428106","https://openalex.org/W3161934848","https://openalex.org/W4214717370","https://openalex.org/W4226353585","https://openalex.org/W4289654392","https://openalex.org/W4313131769","https://openalex.org/W4313588544","https://openalex.org/W4320713398","https://openalex.org/W4321437105","https://openalex.org/W4362510712","https://openalex.org/W4383268742","https://openalex.org/W4385245566","https://openalex.org/W4386017933","https://openalex.org/W6676497082","https://openalex.org/W6848888275"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0],"captioning":[1,22],"involves":[2,142],"generating":[3],"a":[4,44,96,109,144],"natural":[5,35],"language":[6,36],"description":[7],"that":[8,115,129,148],"accurately":[9],"represents":[10],"the":[11,39,118,135,140,155,159,165,169],"content":[12],"and":[13,28,34,54,67,81,83,123,168],"context":[14],"of":[15,41,46,63,98,137],"an":[16],"image.":[17],"To":[18,133],"achieve":[19],"this,":[20],"image":[21,42,138],"utilises":[23],"various":[24],"machine":[25],"learning":[26,56,71],"techniques":[27],"fields,":[29],"such":[30,77],"as":[31,69,78],"computer":[32],"vision":[33],"processing.":[37],"In":[38],"field":[40],"captioning,":[43],"lot":[45],"advances":[47],"have":[48],"been":[49],"made":[50],"with":[51,158],"encoder-decoder":[52],"models":[53],"reinforcement":[55,70],"algorithms.":[57],"However,":[58],"there":[59],"are":[60,130],"still":[61],"problems":[62],"imbalance":[64],"between":[65,120],"testing":[66],"training,":[68],"only":[72],"handles":[73],"single":[74],"comparator":[75],"metrics":[76,90,125,152],"CIDEr,":[79],"SPICE,":[80],"BLEU":[82],"could":[84],"not":[85],"perform":[86],"better":[87],"in":[88,103],"multiple":[89,150],"at":[91],"once.":[92],"Which":[93],"is":[94],"why":[95],"lack":[97],"diversity":[99],"can":[100,116],"be":[101],"seen":[102],"generated":[104,156],"captions.":[105],"This":[106],"idea":[107],"proposes":[108],"general":[110],"technique":[111],"for":[112],"collaborative":[113],"updating":[114,171],"bridge":[117],"gap":[119],"evaluation":[121,151],"measures":[122],"test":[124],"to":[126,153],"produce":[127],"captions":[128],"more":[131],"human-like.":[132],"increase":[134],"precision":[136],"captions,":[139],"approach":[141],"using":[143],"compiled":[145],"reward":[146,170],"system":[147],"considers":[149],"compare":[154],"sentence":[157],"provided":[160],"sentences.":[161],"We":[162],"will":[163],"evaluate":[164],"model's":[166],"performance":[167],"process":[172],"on":[173],"standard":[174],"datasets":[175],"like":[176],"MS":[177],"COCO.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}