{"id":"https://openalex.org/W4220798687","doi":"https://doi.org/10.1109/access.2022.3161428","title":"Deep Learning Approaches Based on Transformer Architectures for Image Captioning Tasks","display_name":"Deep Learning Approaches Based on Transformer Architectures for Image Captioning Tasks","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4220798687","doi":"https://doi.org/10.1109/access.2022.3161428"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3161428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161428","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09739703.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09739703.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064282961","display_name":"Roberto Castro","orcid":"https://orcid.org/0000-0001-8535-1763"},"institutions":[{"id":"https://openalex.org/I3130401523","display_name":"Universidad Yachay Tech","ror":"https://ror.org/04jjswc10","country_code":"EC","type":"education","lineage":["https://openalex.org/I3130401523"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Roberto Castro","raw_affiliation_strings":["Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"],"raw_orcid":"https://orcid.org/0000-0001-8535-1763","affiliations":[{"raw_affiliation_string":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador","institution_ids":["https://openalex.org/I3130401523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071753179","display_name":"Israel Pineda","orcid":"https://orcid.org/0000-0002-3950-2169"},"institutions":[{"id":"https://openalex.org/I3130401523","display_name":"Universidad Yachay Tech","ror":"https://ror.org/04jjswc10","country_code":"EC","type":"education","lineage":["https://openalex.org/I3130401523"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Israel Pineda","raw_affiliation_strings":["Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"],"raw_orcid":"https://orcid.org/0000-0002-3950-2169","affiliations":[{"raw_affiliation_string":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador","institution_ids":["https://openalex.org/I3130401523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006943300","display_name":"Wansu Lim","orcid":"https://orcid.org/0000-0003-2533-3496"},"institutions":[{"id":"https://openalex.org/I113409471","display_name":"Kumoh National Institute of Technology","ror":"https://ror.org/05dkjfz60","country_code":"KR","type":"education","lineage":["https://openalex.org/I113409471"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wansu Lim","raw_affiliation_strings":["Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Future Communications and Systems Laboratory (FCSL), Kumoh National Institute of Technology, Gumi-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2533-3496","affiliations":[{"raw_affiliation_string":"Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Future Communications and Systems Laboratory (FCSL), Kumoh National Institute of Technology, Gumi-si, Republic of Korea","institution_ids":["https://openalex.org/I113409471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088350698","display_name":"Manuel Eugenio Morocho-Cayamcela","orcid":"https://orcid.org/0000-0002-4705-7923"},"institutions":[{"id":"https://openalex.org/I3130401523","display_name":"Universidad Yachay Tech","ror":"https://ror.org/04jjswc10","country_code":"EC","type":"education","lineage":["https://openalex.org/I3130401523"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Manuel Eugenio Morocho-Cayamcela","raw_affiliation_strings":["Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"],"raw_orcid":"https://orcid.org/0000-0002-4705-7923","affiliations":[{"raw_affiliation_string":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador","institution_ids":["https://openalex.org/I3130401523"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.4672,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.9616961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"33679","last_page":"33694"},"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":0.9991000294685364,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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":0.8733842372894287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7892216444015503},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5385400652885437},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5256444215774536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088024735450745},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4931318461894989},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.45714783668518066},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4566679298877716},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4505586326122284},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4338894188404083},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41523459553718567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30439677834510803},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27922484278678894},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.25580257177352905},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19166859984397888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.152145117521286},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11888375878334045}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8733842372894287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892216444015503},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5385400652885437},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5256444215774536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088024735450745},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4931318461894989},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.45714783668518066},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4566679298877716},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4505586326122284},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4338894188404083},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41523459553718567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30439677834510803},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27922484278678894},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25580257177352905},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19166859984397888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.152145117521286},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11888375878334045},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3161428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161428","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09739703.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8fea6da931654af09bd4e411c0513d2e","is_oa":false,"landing_page_url":"https://doaj.org/article/8fea6da931654af09bd4e411c0513d2e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 33679-33694 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3161428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161428","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09739703.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G3801796047","display_name":null,"funder_award_id":"2021R1I1A3056900","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4902169315","display_name":null,"funder_award_id":"2020R1A4A101777511","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6788343825","display_name":null,"funder_award_id":"S3010704","funder_id":"https://openalex.org/F4320327819","funder_display_name":"Ministry of SMEs and Startups"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320327819","display_name":"Ministry of SMEs and Startups","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220798687.pdf","grobid_xml":"https://content.openalex.org/works/W4220798687.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1484210532","https://openalex.org/W1600535962","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W1969616664","https://openalex.org/W2038175477","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2160746645","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2896457183","https://openalex.org/W2963084599","https://openalex.org/W2964308564","https://openalex.org/W2971675178","https://openalex.org/W2997591391","https://openalex.org/W3013128006","https://openalex.org/W3083321496","https://openalex.org/W3109530205","https://openalex.org/W3124149278","https://openalex.org/W3148223059","https://openalex.org/W3215023232","https://openalex.org/W4287755362","https://openalex.org/W6628927728","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639118148","https://openalex.org/W6679434410","https://openalex.org/W6680834391","https://openalex.org/W6682137061","https://openalex.org/W6685230081","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6767415207","https://openalex.org/W6780169642","https://openalex.org/W6789705400"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4376626823"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"onvisual":[3],"attention,":[4],"a":[5,87,98,105,111,132,138,160,180,232],"state-of-the-art":[6],"approach":[7],"for":[8,150,198],"image":[9,213],"captioning":[10,55,153],"tasks":[11],"within":[12],"the":[13,20,39,44,48,54,60,72,94,145,151,185,199,219,223,237],"computer":[14],"vision":[15,208],"research":[16],"area.":[17],"We":[18],"study":[19],"impact":[21,53],"that":[22,38,86,127],"different":[23],"hyperparemeter":[24],"configurations":[25],"on":[26],"an":[27,122,227],"encoder-decoder":[28],"visual":[29],"attention":[30],"architecture":[31],"in":[32,236],"terms":[33],"of":[34,42,89,102,108,114,135,140,187,194,222,234],"efficiency.":[35],"Results":[36],"show":[37,126],"correct":[40],"selection":[41],"both":[43],"cost":[45,186],"function":[46],"and":[47,67,81,104,137,168,196,201,211],"gradient-based":[49],"optimizer":[50],"can":[51],"significantly":[52],"results.":[56],"Our":[57,124],"system":[58],"considers":[59],"cross-entropy,":[61],"Kullback-Leibler":[62],"divergence,":[63],"mean":[64],"squared":[65],"error,":[66],"negative":[68],"log-likelihood":[69],"loss":[70],"functions;":[71],"adaptive":[73],"momentum":[74],"(Adam),":[75],"AdamW,":[76],"RMSprop,":[77],"stochastic":[78],"gradient":[79],"descent,":[80],"Adadelta":[82],"optimizers.":[83],"Experimentation":[84],"shows":[85],"combination":[88],"cross-entropy":[90],"with":[91,131,165],"Adam":[92],"is":[93],"best":[95,146],"alternative":[96,115,164],"returning":[97],"Top-5":[99,133,202],"accuracy":[100,134],"value":[101,107,233],"73.092":[103],"BLEU-4":[106,139,200,238],"20.10.":[109],"Furthermore,":[110],"comparative":[112],"analysis":[113],"convolutional":[116,220],"architectures":[117],"demonstrated":[118],"their":[119],"performance":[120],"as":[121,144],"encoder.":[123],"results":[125],"ResNext-101":[128],"stands":[129],"out":[130],"73.128":[136],"19.80;":[141],"positioning":[142],"itself":[143],"option":[147],"when":[148,206],"looking":[149],"optimum":[152],"quality.":[154],"However,":[155],"MobileNetV3":[156,178],"proved":[157],"to":[158,217],"be":[159],"much":[161],"more":[162],"compact":[163],"2,971,952":[166],"parameters":[167],"0.23":[169],"Giga":[170],"fixed-point":[171],"Multiply-Accumulate":[172],"operations":[173],"per":[174],"Second":[175],"(GMACS).":[176],"Consequently,":[177],"offers":[179],"competitive":[181],"output":[182],"quality":[183],"at":[184],"lower":[188],"computational":[189],"performance,":[190],"supported":[191],"by":[192],"values":[193],"19.50":[195],"72.928":[197],"accuracy,":[203],"respectively.":[204],"Finally,":[205],"testing":[207],"transformer":[209,214],"(ViT),":[210],"data-efficient":[212],"(DeiT)":[215],"models":[216],"replace":[218],"component":[221],"architecture,":[224],"DeiT":[225],"achieved":[226],"improvement":[228],"over":[229],"ViT,":[230],"obtaining":[231],"34.44":[235],"metric.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}