{"id":"https://openalex.org/W3209863343","doi":"https://doi.org/10.1109/icccnt51525.2021.9579897","title":"Hybrid Feature and Sequence Extractor based Deep Learning Model for Image Caption Generation","display_name":"Hybrid Feature and Sequence Extractor based Deep Learning Model for Image Caption Generation","publication_year":2021,"publication_date":"2021-07-06","ids":{"openalex":"https://openalex.org/W3209863343","doi":"https://doi.org/10.1109/icccnt51525.2021.9579897","mag":"3209863343"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt51525.2021.9579897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5037819685","display_name":"Rohit Kushwaha","orcid":"https://orcid.org/0000-0002-8217-3348"},"institutions":[{"id":"https://openalex.org/I151903974","display_name":"National Institute Of Technology Silchar","ror":"https://ror.org/001ws2a36","country_code":"IN","type":"education","lineage":["https://openalex.org/I151903974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohit Kushwaha","raw_affiliation_strings":["National Institute of Technology Silchar, Silchar, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Silchar, Silchar, Assam, India","institution_ids":["https://openalex.org/I151903974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078136113","display_name":"Anupam Biswas","orcid":"https://orcid.org/0000-0003-0756-6026"},"institutions":[{"id":"https://openalex.org/I151903974","display_name":"National Institute Of Technology Silchar","ror":"https://ror.org/001ws2a36","country_code":"IN","type":"education","lineage":["https://openalex.org/I151903974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anupam Biswas","raw_affiliation_strings":["National Institute of Technology Silchar, Silchar, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Silchar, Silchar, Assam, India","institution_ids":["https://openalex.org/I151903974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3881,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.61966742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9970999956130981,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.8618090152740479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.732310950756073},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6759288311004639},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6408683061599731},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5475432276725769},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.52886563539505},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5007164478302002},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4947058856487274},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4869743287563324},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.47966909408569336},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46209779381752014},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4568399488925934},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4170326590538025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33557090163230896},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.20307603478431702},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09936362504959106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618090152740479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.732310950756073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6759288311004639},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6408683061599731},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5475432276725769},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.52886563539505},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5007164478302002},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4947058856487274},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4869743287563324},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.47966909408569336},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46209779381752014},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4568399488925934},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4170326590538025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33557090163230896},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.20307603478431702},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09936362504959106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt51525.2021.9579897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2119775030","https://openalex.org/W2171361956","https://openalex.org/W2899476708","https://openalex.org/W2900758523","https://openalex.org/W2964121744","https://openalex.org/W2977928982","https://openalex.org/W3093686763","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6677994088","https://openalex.org/W6685230081","https://openalex.org/W6756407008"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W1590965489","https://openalex.org/W1875930651"],"abstract_inverted_index":{"Generating":[0],"the":[1,4,40,58,63,67,74,89,92,98,102,104,116,119,124,128,139],"captions":[2,38,69],"from":[3,62,70],"input":[5,41],"images":[6],"is":[7,47,81,85,106,121],"a":[8,25,50],"crucial":[9],"problem,":[10],"it":[11],"includes":[12],"both":[13],"computer":[14],"vision":[15],"and":[16,28,115],"natural":[17],"language":[18],"processing.":[19],"In":[20,101],"this":[21],"paper,":[22],"we":[23],"introduced":[24],"hybrid":[26],"feature":[27,60,72],"sequence":[29],"extractor-based":[30],"deep":[31,51],"learning":[32],"model":[33,46,84,105,120,136],"that":[34],"helps":[35],"in":[36],"generating":[37],"for":[39,56],"images.":[42,64],"The":[43,83],"proposed":[44],"generative":[45],"designed":[48],"using":[49],"convolution":[52],"neural":[53],"network":[54,80],"(VGG-19)":[55],"extracting":[57],"salient":[59],"vectors":[61],"While":[65],"producing":[66],"informative":[68],"these":[71],"vectors,":[73],"LSTM":[75],"(Long":[76],"Short":[77],"Term":[78],"Memory)":[79],"utilized.":[82],"trained":[86,107],"to":[87,97,131],"expand":[88],"probability":[90],"of":[91,118],"target":[93],"description":[94],"sentence":[95],"delivered":[96],"training":[99],"image.":[100],"analysis,":[103],"with":[108,142],"very":[109],"renowned":[110],"data":[111],"sets":[112],"like":[113],"FLICKR-8K,":[114],"correctness":[117],"calculated":[122],"utilizing":[123],"BLEU":[125,140],"score":[126,141],"granting":[127],"range":[129],"0":[130],"100.":[132],"We":[133],"compare":[134],"our":[135],"based":[137],"on":[138],"four":[143],"other":[144],"models.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}