{"id":"https://openalex.org/W4295789413","doi":"https://doi.org/10.1109/spicscon54707.2021.9885414","title":"Implementing Deep Neural Network Based Encoder-Decoder Framework for Image Captioning","display_name":"Implementing Deep Neural Network Based Encoder-Decoder Framework for Image Captioning","publication_year":2021,"publication_date":"2021-12-03","ids":{"openalex":"https://openalex.org/W4295789413","doi":"https://doi.org/10.1109/spicscon54707.2021.9885414"},"language":"en","primary_location":{"id":"doi:10.1109/spicscon54707.2021.9885414","doi":"https://doi.org/10.1109/spicscon54707.2021.9885414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spicscon54707.2021.9885414","pdf_url":null,"source":{"id":"https://openalex.org/S7407097036","display_name":"IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5100721655","display_name":"Md. Mijanur Rahman","orcid":"https://orcid.org/0000-0001-5957-6483","observed_orcids":["https://orcid.org/0000-0001-5957-6483","https://orcid.org/0000-0002-7921-7725"]},"institutions":[{"id":"https://openalex.org/I11000651","display_name":"Jatiya Kabi Kazi Nazrul Islam University","ror":"https://ror.org/009kcw598","country_code":"BD","type":"education","lineage":["https://openalex.org/I11000651"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Mijanur Rahman","raw_affiliation_strings":["Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","institution_ids":["https://openalex.org/I11000651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I11000651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054753786","display_name":"Ashik Uzzaman","orcid":"https://orcid.org/0009-0006-2386-6503","observed_orcids":["https://orcid.org/0009-0006-2386-6503"]},"institutions":[{"id":"https://openalex.org/I11000651","display_name":"Jatiya Kabi Kazi Nazrul Islam University","ror":"https://ror.org/009kcw598","country_code":"BD","type":"education","lineage":["https://openalex.org/I11000651"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ashik Uzzaman","raw_affiliation_strings":["Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","institution_ids":["https://openalex.org/I11000651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I11000651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017232782","display_name":"Sadia Islam Sami","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I11000651","display_name":"Jatiya Kabi Kazi Nazrul Islam University","ror":"https://ror.org/009kcw598","country_code":"BD","type":"education","lineage":["https://openalex.org/I11000651"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sadia Islam Sami","raw_affiliation_strings":["Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jatiya Kabi Kazi Nazrul Islam University,Department of Computer Science and Engineering,Trishal,Mymensingh,Bangladesh","institution_ids":["https://openalex.org/I11000651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Trishal, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I11000651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11000651"],"apc_list":null,"apc_paid":null,"fwci":0.2311,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51220104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.00039999998989515007,"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":0.0003000000142492354,"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/image-captioning","display_name":"image captioning","score":0.9369999766349792},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.859000027179718},{"id":"https://openalex.org/keywords/cnn-encoder","display_name":"CNN encoder","score":0.7049999833106995},{"id":"https://openalex.org/keywords/lstm-decoder","display_name":"LSTM decoder","score":0.9990000128746033},{"id":"https://openalex.org/keywords/vgg19","display_name":"VGG19","score":0.9120000004768372},{"id":"https://openalex.org/keywords/image-feature-extraction","display_name":"image feature extraction","score":0.8450000286102295},{"id":"https://openalex.org/keywords/text-generation","display_name":"text generation","score":0.6019999980926514},{"id":"https://openalex.org/keywords/ms-coco","display_name":"MS COCO","score":0.9700000286102295},{"id":"https://openalex.org/keywords/bleu-evaluation","display_name":"BLEU evaluation","score":0.9769999980926514}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9524000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6762999892234802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26980000734329224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spicscon54707.2021.9885414","doi":"https://doi.org/10.1109/spicscon54707.2021.9885414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spicscon54707.2021.9885414","pdf_url":null,"source":{"id":"https://openalex.org/S7407097036","display_name":"IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1521626219","https://openalex.org/W1527575280","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1934890906","https://openalex.org/W2006147162","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2185175083","https://openalex.org/W2282219577","https://openalex.org/W2302086703","https://openalex.org/W2338131049","https://openalex.org/W2339652278","https://openalex.org/W2510850444","https://openalex.org/W2896842408","https://openalex.org/W2922806964","https://openalex.org/W2953322005","https://openalex.org/W2962968665","https://openalex.org/W3000154564","https://openalex.org/W3111746241","https://openalex.org/W3129738317","https://openalex.org/W6676497082","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4297890714","https://openalex.org/W4404727707","https://openalex.org/W4385422156","https://openalex.org/W2766561237","https://openalex.org/W4378983079","https://openalex.org/W4395955659","https://openalex.org/W4401754183","https://openalex.org/W4285279172","https://openalex.org/W4390693720","https://openalex.org/W4392896648"],"abstract_inverted_index":{"This":[0],"study":[1],"is":[2,80,103],"concerned":[3],"with":[4,168],"the":[5,49,73,90,95,100,107,120,159,175,181,184,188],"development":[6],"of":[7,134,183],"a":[8,14,21,40,52,124,129],"deep":[9],"neural":[10,16,97],"network-based":[11,98],"framework,":[12],"including":[13],"\u201cconvolutional":[15],"network":[17,78],"(CNN)\u201d":[18],"encoder":[19,54],"and":[20,42,60,85,115,118,146,151,170,179],"\u201cLong":[22],"Short-Term":[23],"Memory":[24],"(LSTM)\u201d":[25],"decoder":[26,79],"in":[27,39,48,63,94],"an":[28,76,111],"automatic":[29,176],"image":[30,112,177],"captioning":[31,178],"application.":[32],"The":[33,162],"proposed":[34,96,108,160,185],"model":[35,102,109,122,186],"percepts":[36],"information":[37,59],"points":[38],"picture":[41],"their":[43],"relationship":[44],"to":[45,68],"one":[46],"another":[47],"viewpoint.":[50],"Firstly,":[51],"CNN":[53],"excels":[55],"at":[56],"retaining":[57],"spatial":[58],"recognizing":[61],"objects":[62],"images":[64,135],"by":[65],"extracting":[66],"features":[67],"produce":[69],"vocabulary":[70],"that":[71],"describes":[72],"photos.":[74],"Secondly,":[75],"LSTM":[77,121],"used":[81,152],"for":[82,105,153],"predicting":[83],"words":[84],"creating":[86],"meaningful":[87],"sentences":[88],"from":[89,136],"built":[91],"keywords.":[92],"Thus,":[93],"system,":[99],"VGG-19":[101],"presented":[104],"defining":[106],"as":[110,128,141,155,157],"feature":[113],"extractor":[114],"sequence":[116],"processor,":[117],"then":[119],"provides":[123],"fixed-length":[125],"output":[126],"vector":[127],"final":[130],"prediction.":[131],"A":[132],"variety":[133],"several":[137],"open-source":[138],"datasets,":[139],"such":[140],"Flickr":[142,144],"8k,":[143],"30k,":[145],"MS":[147],"COCO,":[148],"were":[149],"explored":[150],"training":[154],"well":[156],"testing":[158],"model.":[161],"experiment":[163],"was":[164],"done":[165],"on":[166],"Python":[167],"Keras":[169],"TensorFlow":[171],"backend.":[172],"It":[173],"demonstrated":[174],"evaluated":[180],"performance":[182],"using":[187],"BLEU":[189],"(BiLingual":[190],"Evaluation":[191],"Understudy)":[192],"metric.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-09-15T00:00:00"}