{"id":"https://openalex.org/W4307264713","doi":"https://doi.org/10.3390/jimaging8110294","title":"Hybrid of Deep Learning and Word Embedding in Generating Captions: Image-Captioning Solution for Geological Rock Images","display_name":"Hybrid of Deep Learning and Word Embedding in Generating Captions: Image-Captioning Solution for Geological Rock Images","publication_year":2022,"publication_date":"2022-10-22","ids":{"openalex":"https://openalex.org/W4307264713","doi":"https://doi.org/10.3390/jimaging8110294","pmid":"https://pubmed.ncbi.nlm.nih.gov/36354867"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging8110294","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging8110294","pdf_url":"https://www.mdpi.com/2313-433X/8/11/294/pdf?version=1666448586","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/8/11/294/pdf?version=1666448586","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027601363","display_name":"Agus Nursikuwagus","orcid":"https://orcid.org/0000-0001-8435-7522"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Agus Nursikuwagus","raw_affiliation_strings":["Doctoral Program of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia"],"raw_orcid":"https://orcid.org/0000-0001-8435-7522","affiliations":[{"raw_affiliation_string":"Doctoral Program of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114045995","display_name":"Rinaldi Munir","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Rinaldi Munir","raw_affiliation_strings":["Department of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031833654","display_name":"Masayu Leylia Khodra","orcid":"https://orcid.org/0000-0002-8765-8109"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Masayu Leylia Khodra","raw_affiliation_strings":["Department of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jl. Ganesha No.10, Bandung 40132, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027601363","https://openalex.org/A5114045995"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1675},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1675},"fwci":0.4972,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60978928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":"11","first_page":"294","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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":0.9866999983787537,"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":0.927841305732727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8001482486724854},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.7405703067779541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.707275390625},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6457805037498474},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5711801648139954},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.561535120010376},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5372990965843201},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5292313098907471},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4688122272491455},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4585523307323456},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4561319947242737},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43418481945991516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38075512647628784},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.24064719676971436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08726921677589417},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.07334914803504944}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.927841305732727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001482486724854},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7405703067779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.707275390625},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6457805037498474},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5711801648139954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.561535120010376},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5372990965843201},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5292313098907471},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4688122272491455},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4585523307323456},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4561319947242737},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43418481945991516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38075512647628784},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.24064719676971436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08726921677589417},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.07334914803504944},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging8110294","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging8110294","pdf_url":"https://www.mdpi.com/2313-433X/8/11/294/pdf?version=1666448586","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:36354867","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36354867","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9693370","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9693370","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:a04880d5f013406093088bca9259fb73","is_oa":true,"landing_page_url":"https://doaj.org/article/a04880d5f013406093088bca9259fb73","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 8, Iss 11, p 294 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging8110294","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging8110294","pdf_url":"https://www.mdpi.com/2313-433X/8/11/294/pdf?version=1666448586","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307264713.pdf","grobid_xml":"https://content.openalex.org/works/W4307264713.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1614298861","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1947481528","https://openalex.org/W2090087086","https://openalex.org/W2101105183","https://openalex.org/W2106527823","https://openalex.org/W2112796928","https://openalex.org/W2162931300","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2526273376","https://openalex.org/W2552161745","https://openalex.org/W2560920409","https://openalex.org/W2625940279","https://openalex.org/W2735305611","https://openalex.org/W2766261529","https://openalex.org/W2790951685","https://openalex.org/W2801271919","https://openalex.org/W2808206191","https://openalex.org/W2808468291","https://openalex.org/W2883112830","https://openalex.org/W2885822952","https://openalex.org/W2888680923","https://openalex.org/W2894669491","https://openalex.org/W2895420168","https://openalex.org/W2895465439","https://openalex.org/W2907158289","https://openalex.org/W2907279673","https://openalex.org/W2909624725","https://openalex.org/W2911285743","https://openalex.org/W2914163459","https://openalex.org/W2962935746","https://openalex.org/W2963686907","https://openalex.org/W2964537485","https://openalex.org/W2968729886","https://openalex.org/W2972093541","https://openalex.org/W2974204346","https://openalex.org/W2980049533","https://openalex.org/W3013439560","https://openalex.org/W3016866130","https://openalex.org/W3027950762","https://openalex.org/W3034689697","https://openalex.org/W3061415658","https://openalex.org/W3080194793","https://openalex.org/W3098358988","https://openalex.org/W3119749398","https://openalex.org/W3153998676","https://openalex.org/W3201379930","https://openalex.org/W4252062406","https://openalex.org/W4288329833","https://openalex.org/W4389081127","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6638549007","https://openalex.org/W6732188011","https://openalex.org/W6751820907","https://openalex.org/W6753043086","https://openalex.org/W6754653261","https://openalex.org/W6755089507","https://openalex.org/W6763643401","https://openalex.org/W6765227454","https://openalex.org/W6777842546"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3217195652","https://openalex.org/W2905749112","https://openalex.org/W2346530426","https://openalex.org/W3101154008","https://openalex.org/W3099354896","https://openalex.org/W2890749918","https://openalex.org/W4287599800","https://openalex.org/W2772765860","https://openalex.org/W4312264180"],"abstract_inverted_index":{"Captioning":[0],"is":[1,51],"the":[2,39,46,55,58,79,122,133,152,210,214],"process":[3],"of":[4,49,57,103,113,132,174,186,198],"assembling":[5],"a":[6,66,87,100,111,119,238],"description":[7],"for":[8,29,151,158],"an":[9],"image.":[10,80],"Previous":[11],"research":[12],"on":[13,18,54],"captioning":[14,22,64],"has":[15],"usually":[16],"focused":[17,53],"foreground":[19,34],"objects.":[20],"In":[21,36],"concepts,":[23],"there":[24,218],"are":[25,219],"two":[26],"main":[27],"objects":[28],"discussion:":[30],"background":[31,56],"object":[32],"and":[33,73,96,98,138,144,168,179,191,203,234],"object.":[35],"contrast":[37],"to":[38,75],"previous":[40],"image-captioning":[41],"research,":[42],"generating":[43],"captions":[44],"from":[45,78],"geological":[47,228,231,239],"images":[48],"rocks":[50],"more":[52],"images.":[59],"This":[60],"study":[61],"proposed":[62,82,140],"image":[63],"using":[65,160],"convolutional":[67,88],"neural":[68,89],"network,":[69],"long":[70,92],"short-term":[71,93],"memory,":[72],"word2vec":[74,97],"generate":[76],"words":[77,115,236],"The":[81,154],"model":[83,136,208],"was":[84,116],"constructed":[85],"by":[86,121,237],"network":[90],"(CNN),":[91],"memory":[94],"(LSTM),":[95],"gave":[99],"dense":[101],"output":[102],"256":[104],"units.":[105],"To":[106],"make":[107],"it":[108],"properly":[109],"grammatical,":[110],"sequence":[112],"predicted":[114],"reconstructed":[117],"into":[118],"sentence":[120,229,232],"beam":[123],"search":[124],"algorithm":[125],"with":[126,184],"K":[127],"=":[128],"3.":[129],"An":[130],"evaluation":[131],"pre-trained":[134],"baseline":[135,215],"VGG16":[137],"our":[139],"CNN-A,":[141],"CNN-B,":[142],"CNN-C,":[143],"CNN-D":[145],"models":[146,162],"used":[147],"BLEU":[148,155],"score":[149],"methods":[150],"N-gram.":[153],"scores":[156,173,185,197],"achieved":[157],"BLEU-1":[159],"these":[161],"were":[163],"0.5515,":[164],"0.6463,":[165],"0.7012,":[166],"0.7620,":[167],"0.5620,":[169],"respectively.":[170,181,193,205],"BLEU-2":[171],"showed":[172],"0.6048,":[175],"0.6507,":[176],"0.7083,":[177],"0.8756,":[178],"0.6578,":[180],"BLEU-3":[182],"performed":[183],"0.6414,":[187],"0.6892,":[188],"0.7312,":[189],"0.8861,":[190],"0.7307,":[192],"Finally,":[194],"BLEU-4":[195],"had":[196],"0.6526,":[199],"0.6504,":[200],"0.7345,":[201],"0.8250,":[202],"0.7537,":[204],"Our":[206],"CNN-C":[207],"outperformed":[209],"other":[211],"models,":[212],"especially":[213],"model.":[216],"Furthermore,":[217],"several":[220],"future":[221],"challenges":[222],"in":[223],"studying":[224],"captions,":[225],"such":[226],"as":[227],"structure,":[230],"phrase,":[233],"constructing":[235],"tagger.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}