{"id":"https://openalex.org/W4390693720","doi":"https://doi.org/10.1109/iccais59597.2023.10382370","title":"Performance Evaluation of CNN-based Encoders for Image Captioning","display_name":"Performance Evaluation of CNN-based Encoders for Image Captioning","publication_year":2023,"publication_date":"2023-11-27","ids":{"openalex":"https://openalex.org/W4390693720","doi":"https://doi.org/10.1109/iccais59597.2023.10382370"},"language":"en","primary_location":{"id":"doi:10.1109/iccais59597.2023.10382370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais59597.2023.10382370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)","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/A5102602560","display_name":"Anh Cong Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159515","display_name":"H\u1ed3ng \u0110\u1ee9c University","ror":"https://ror.org/05dp8mg49","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210159515"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Anh Cong Hoang","raw_affiliation_strings":["Thanh Hoa University of Culture, Sports and Tourism,Thanh Hoa,Viet Nam","Thanh Hoa University of Culture, Sports and Tourism, Thanh Hoa, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Thanh Hoa University of Culture, Sports and Tourism,Thanh Hoa,Viet Nam","institution_ids":["https://openalex.org/I4210159515"]},{"raw_affiliation_string":"Thanh Hoa University of Culture, Sports and Tourism, Thanh Hoa, Viet Nam","institution_ids":["https://openalex.org/I4210159515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925307","display_name":"Dinh Cong Nguyen","orcid":"https://orcid.org/0000-0003-0798-5511"},"institutions":[{"id":"https://openalex.org/I4210159515","display_name":"H\u1ed3ng \u0110\u1ee9c University","ror":"https://ror.org/05dp8mg49","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210159515"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh Cong Nguyen","raw_affiliation_strings":["Hong Duc University,Thanh Hoa,Viet Nam","Hong Duc University, Thanh Hoa, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Hong Duc University,Thanh Hoa,Viet Nam","institution_ids":["https://openalex.org/I4210159515"]},{"raw_affiliation_string":"Hong Duc University, Thanh Hoa, Viet Nam","institution_ids":["https://openalex.org/I4210159515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100623041","display_name":"Long Hoang Nguyen","orcid":"https://orcid.org/0000-0003-1658-2394"},"institutions":[{"id":"https://openalex.org/I4210159515","display_name":"H\u1ed3ng \u0110\u1ee9c University","ror":"https://ror.org/05dp8mg49","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210159515"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoang Long Nguyen","raw_affiliation_strings":["Hong Duc University,Thanh Hoa,Viet Nam","Hong Duc University, Thanh Hoa, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Hong Duc University,Thanh Hoa,Viet Nam","institution_ids":["https://openalex.org/I4210159515"]},{"raw_affiliation_string":"Hong Duc University, Thanh Hoa, Viet Nam","institution_ids":["https://openalex.org/I4210159515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102602560"],"corresponding_institution_ids":["https://openalex.org/I4210159515"],"apc_list":null,"apc_paid":null,"fwci":0.2456,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5546145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"217"},"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":0.9973999857902527,"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":0.9957000017166138,"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":0.9357204437255859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.889686107635498},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6800703406333923},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6755068898200989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6434861421585083},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5883480310440063},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5540062785148621},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4786733090877533},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4756088852882385},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4698200523853302},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39315247535705566},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37020784616470337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36291033029556274},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3420845866203308},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.08290815353393555}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9357204437255859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889686107635498},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6800703406333923},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6755068898200989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434861421585083},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5883480310440063},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5540062785148621},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4786733090877533},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4756088852882385},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4698200523853302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39315247535705566},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37020784616470337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36291033029556274},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3420845866203308},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.08290815353393555},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais59597.2023.10382370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais59597.2023.10382370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)","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":35,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2295744208","https://openalex.org/W2549139847","https://openalex.org/W2552161745","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2896348597","https://openalex.org/W2943885184","https://openalex.org/W2962982762","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963740313","https://openalex.org/W2999219213","https://openalex.org/W3010079658","https://openalex.org/W3138516171","https://openalex.org/W4221144572","https://openalex.org/W4386162736","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6637306801","https://openalex.org/W6638742206","https://openalex.org/W6679434410","https://openalex.org/W6697306443","https://openalex.org/W6762718338","https://openalex.org/W6797674293","https://openalex.org/W6810471750"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3066373881","https://openalex.org/W2971257618","https://openalex.org/W2955428276"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"automatically":[2],"generates":[3],"syntactically":[4],"and":[5,15,38,67,77,89,109,121,131],"semantically":[6],"correct":[7],"descriptions":[8],"for":[9],"images.":[10],"To":[11],"construct":[12],"an":[13,86],"accurate":[14,98],"efficient":[16],"system,":[17],"the":[18,23,33,44,70,74,81,135],"feature":[19],"extraction":[20],"step":[21,30],"from":[22,59,80],"image":[24],"plays":[25],"a":[26],"crucial":[27],"role.":[28],"This":[29],"involves":[31],"identifying":[32],"main":[34],"objects,":[35],"their":[36],"attributes,":[37],"possible":[39],"relationships":[40],"between":[41],"objects":[42],"in":[43,54],"image.":[45,82],"Convolutional":[46],"neural":[47],"network":[48],"(CNN)-based":[49],"technologies":[50],"have":[51],"shown":[52],"advantages":[53],"these":[55],"tasks.":[56],"Drawing":[57],"inspiration":[58],"encoder-decoder":[60],"architectures,":[61],"this":[62,138],"research":[63],"proposes":[64],"several":[65],"modifications":[66],"updates":[68],"to":[69,72,96],"encoder":[71],"extract":[73],"most":[75],"important":[76],"concise":[78],"features":[79],"The":[83,100,123],"decoder":[84],"utilizes":[85],"attention":[87],"module":[88],"Long":[90],"short":[91],"term":[92],"memory":[93],"(LSTM)":[94],"models":[95,114],"generate":[97],"captions.":[99],"experiments":[101],"are":[102,125],"evaluated":[103],"on":[104],"two":[105],"datasets":[106],"as":[107,116],"Flickr8k":[108],"Flickr30k":[110],"with":[111],"various":[112],"pretrained":[113],"such":[115],"ResNet101,":[117],"Swin-Transformer,":[118],"ConvNeXt,":[119],"EfficientNet,":[120],"ResNeXt.":[122],"results":[124],"assessed":[126],"using":[127],"BLEU-1,":[128],"BLEU-2,":[129],"BLEU-3,":[130],"BLEU-4":[132],"metrics,":[133],"demonstrating":[134],"potential":[136],"of":[137],"approach.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}