{"id":"https://openalex.org/W4379653879","doi":"https://doi.org/10.1117/12.2680670","title":"Reinforcement learning transformer for image captioning generation model","display_name":"Reinforcement learning transformer for image captioning generation model","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379653879","doi":"https://doi.org/10.1117/12.2680670"},"language":"en","primary_location":{"id":"doi:10.1117/12.2680670","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2680670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","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/A5100579393","display_name":"Zhaojie Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaojie Yan","raw_affiliation_strings":["Univ. of California, Santa Barbara (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of California, Santa Barbara (United States)","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100579393"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.2316,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49586109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.934499979019165,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.919700026512146,"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":0.9230082631111145},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7974073886871338},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7887139916419983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556778192520142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5197715163230896},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48100146651268005},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4437524974346161},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2867932915687561},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16727179288864136},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16407859325408936},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09342652559280396}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9230082631111145},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7974073886871338},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7887139916419983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556778192520142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5197715163230896},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48100146651268005},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4437524974346161},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2867932915687561},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16727179288864136},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16407859325408936},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09342652559280396},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2680670","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2680670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"generation":[2],"is":[3,42],"a":[4,80],"combination":[5],"of":[6,47,57,66],"the":[7,19,37,45,51,58,63,67,74],"visual":[8],"domain":[9],"and":[10,27,34],"natural":[11],"language":[12],"processing.":[13],"The":[14,69],"transformer":[15,28,76],"framework":[16],"has":[17,54,78],"become":[18],"mainstream":[20],"approach.":[21],"This":[22],"paper":[23],"combines":[24],"reinforcement":[25,48,75],"learning":[26,49],"methods":[29],"to":[30],"reward":[31],"dynamics":[32],"backpropagation":[33],"normalization":[35],"in":[36,83],"testing":[38],"phase.":[39],"Its":[40],"characteristic":[41],"that":[43,73],"when":[44],"steps":[46],"increase,":[50],"agent":[52],"model":[53],"more":[55],"knowledge":[56],"fully":[59],"information,":[60],"which":[61],"reduces":[62],"computing":[64],"cost":[65],"system.":[68],"experimental":[70],"results":[71],"show":[72],"structure":[77],"achieved":[79],"certain":[81],"improvement":[82],"speed.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}