{"id":"https://openalex.org/W4400810498","doi":"https://doi.org/10.1109/access.2024.3431091","title":"Enhanced Image Captioning Using Bahdanau Attention Mechanism and Heuristic Beam Search Algorithm","display_name":"Enhanced Image Captioning Using Bahdanau Attention Mechanism and Heuristic Beam Search Algorithm","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400810498","doi":"https://doi.org/10.1109/access.2024.3431091"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3431091","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3431091","pdf_url":null,"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":null,"license_id":null,"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://doi.org/10.1109/access.2024.3431091","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054930513","display_name":"S. Abinaya","orcid":"https://orcid.org/0000-0001-7957-7934"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Abinaya","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0001-7957-7934","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024625944","display_name":"M Lakshmi Deepak","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mandava Deepak","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039410557","display_name":"A. Sherly Alphonse","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A. Sherly Alphonse","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0002-0019-9940","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.2903,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89462161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"100991","last_page":"101003"},"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":0.9923999905586243,"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":0.991100013256073,"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":0.9310656785964966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8742575645446777},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6127476096153259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6059857606887817},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.597355842590332},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5570929050445557},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5185295343399048},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5051830410957336},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4985926151275635},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4695485234260559},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4356918931007385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40061792731285095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37211161851882935},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3704771399497986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3491954803466797},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3155452013015747}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9310656785964966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8742575645446777},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6127476096153259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6059857606887817},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.597355842590332},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5570929050445557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5185295343399048},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5051830410957336},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4985926151275635},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4695485234260559},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4356918931007385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40061792731285095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37211161851882935},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3704771399497986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3491954803466797},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3155452013015747},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3431091","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3431091","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c191fc72e6a5463b8fd9d691ddc53b1b","is_oa":true,"landing_page_url":"https://doaj.org/article/c191fc72e6a5463b8fd9d691ddc53b1b","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":"IEEE Access, Vol 12, Pp 100991-101003 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3431091","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3431091","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319346","display_name":"Vellore Institute of Technology, Chennai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2481240925","https://openalex.org/W2575842049","https://openalex.org/W2977928982","https://openalex.org/W3005983418","https://openalex.org/W3020496924","https://openalex.org/W3090988983","https://openalex.org/W3093225449","https://openalex.org/W3151908889","https://openalex.org/W3163431160","https://openalex.org/W4281633595","https://openalex.org/W4283835934","https://openalex.org/W4285491539","https://openalex.org/W4296143946","https://openalex.org/W4319594886","https://openalex.org/W4319596633","https://openalex.org/W4323055215","https://openalex.org/W4324129116","https://openalex.org/W4361298885","https://openalex.org/W4379276824","https://openalex.org/W4381195770","https://openalex.org/W4386494644","https://openalex.org/W4387268351","https://openalex.org/W6639657675","https://openalex.org/W6839015040"],"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/W4289422896"],"abstract_inverted_index":{"Captioning":[0],"images":[1],"is":[2],"a":[3,55,75,89],"challenging":[4],"task":[5],"at":[6],"the":[7,25,104,126],"intersection":[8],"of":[9,27,57,128,145,154],"Computer":[10],"Vision":[11],"(CV)":[12],"and":[13,41,65,88,114,120,139,147,158,173],"Natural":[14],"Language":[15],"Processing":[16],"(NLP),":[17],"that":[18,80],"involves":[19],"generating":[20,47],"descriptive":[21],"text":[22],"to":[23,61,66,108],"depict":[24],"content":[26],"an":[28],"image.":[29],"Existing":[30],"methodologies":[31],"typically":[32],"employ":[33],"Convolutional":[34],"Neural":[35,43],"Networks":[36,44],"(CNNs)":[37],"for":[38,46,83,95,118,177],"feature":[39,86],"extraction":[40,87],"Recurrent":[42],"(RNNs)":[45],"captions.":[48,69],"However,":[49],"these":[50],"approaches":[51],"often":[52],"suffer":[53],"from":[54],"lack":[56],"contextual":[58],"understanding,":[59],"inability":[60],"capture":[62],"fine-grained":[63],"details,":[64],"generate":[67],"generic":[68],"This":[70],"study":[71],"proposes":[72],"VisualCaptionNet":[73],"(VCN),":[74],"novel":[76],"image":[77,112,167],"captioning":[78,168],"model":[79],"leverages":[81],"ResNet50":[82],"rich":[84],"visual":[85],"Long":[90],"Short-Term":[91],"Memory":[92],"(LSTM)":[93],"network":[94],"sequential":[96],"caption":[97,155],"generation":[98],"while":[99],"retaining":[100],"context.":[101],"By":[102],"incorporating":[103],"Bahdanau":[105],"attention":[106],"mechanism":[107],"focus":[109],"on":[110,133],"relevant":[111,122,175],"regions":[113],"integrating":[115],"beam":[116],"search":[117],"coherent":[119],"contextually":[121,174],"descriptions,":[123],"VCN":[124],"addresses":[125],"limitations":[127],"previous":[129],"methodologies.":[130],"Extensive":[131],"experimentation":[132],"benchmark":[134],"datasets":[135],"such":[136],"as":[137],"Flickr30K":[138],"Flickr8K":[140],"demonstrates":[141],"VCN\u2019s":[142,163],"notable":[143],"improvements":[144],"10%":[146],"12%":[148],"over":[149],"baseline":[150],"models":[151],"in":[152,165],"terms":[153],"quality,":[156],"coherence,":[157],"relevance.":[159],"These":[160],"enhancements":[161],"emphasize":[162],"effectiveness":[164],"advancing":[166],"tasks,":[169],"promising":[170],"more":[171],"accurate":[172],"descriptions":[176],"images.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}