{"id":"https://openalex.org/W4388938144","doi":"https://doi.org/10.1109/icccnt56998.2023.10308085","title":"A Review on Automatic Image Caption Generation for Various Deep Learning Approaches","display_name":"A Review on Automatic Image Caption Generation for Various Deep Learning Approaches","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4388938144","doi":"https://doi.org/10.1109/icccnt56998.2023.10308085"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt56998.2023.10308085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10308085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"},"type":"review","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/A5048046961","display_name":"Arun Singh","orcid":"https://orcid.org/0000-0002-9712-9921"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arun Pratap Singh","raw_affiliation_strings":["Samrat Ashok Technological Institute,Computer Science &#x0026; Engineering,Vidisha,Madhya Pradesh,India"],"affiliations":[{"raw_affiliation_string":"Samrat Ashok Technological Institute,Computer Science &#x0026; Engineering,Vidisha,Madhya Pradesh,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088999117","display_name":"Manish Manoria","orcid":"https://orcid.org/0000-0002-5742-3640"},"institutions":[{"id":"https://openalex.org/I4210143989","display_name":"Bansal Institute Of Research Technology & Science","ror":"https://ror.org/03tg26f52","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143989"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Manoria","raw_affiliation_strings":["Bansal Institute of Research Technology &#x0026; Science,Computer Science &#x0026; Engineering,Bhopal,Madhya Pradesh,India"],"affiliations":[{"raw_affiliation_string":"Bansal Institute of Research Technology &#x0026; Science,Computer Science &#x0026; Engineering,Bhopal,Madhya Pradesh,India","institution_ids":["https://openalex.org/I4210143989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010070997","display_name":"Sunil Joshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil Joshi","raw_affiliation_strings":["Samrat Ashok Technological Institute,Computer Science &#x0026; Engineering,Vidisha,Madhya Pradesh,India"],"affiliations":[{"raw_affiliation_string":"Samrat Ashok Technological Institute,Computer Science &#x0026; Engineering,Vidisha,Madhya Pradesh,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048046961"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8597,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7613424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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":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/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9696000218391418,"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":0.9529353380203247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8751081824302673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7638288736343384},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6672406196594238},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6491810083389282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5477764010429382},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.546883225440979},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5385473966598511},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5163937211036682},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4658931493759155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4619140625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3739376664161682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3735870122909546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32043182849884033}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9529353380203247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8751081824302673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7638288736343384},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6672406196594238},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6491810083389282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5477764010429382},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.546883225440979},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5385473966598511},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5163937211036682},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4658931493759155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4619140625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3739376664161682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3735870122909546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32043182849884033},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt56998.2023.10308085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10308085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1570121212","https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W2065424327","https://openalex.org/W2114841702","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2430258811","https://openalex.org/W2604729005","https://openalex.org/W2607151106","https://openalex.org/W2786942787","https://openalex.org/W2790776232","https://openalex.org/W2790781626","https://openalex.org/W2890718122","https://openalex.org/W2908056713","https://openalex.org/W2913836951","https://openalex.org/W2941328520","https://openalex.org/W2962935746","https://openalex.org/W2964616647","https://openalex.org/W3003978108","https://openalex.org/W3036170638","https://openalex.org/W3130753774","https://openalex.org/W3145035686","https://openalex.org/W3157126855","https://openalex.org/W3163906087","https://openalex.org/W6677231853","https://openalex.org/W6717635511"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"In":[0],"machine":[1,162,174],"learning,":[2],"image":[3,20,32,59,204],"captioning":[4,33,50,205],"is":[5,34,51,65,143,146,153,164,196],"a":[6,52],"process":[7],"of":[8,45,58,160,173,187,193],"extracting":[9],"information":[10],"as":[11,85,112,148],"per":[12],"the":[13,38,43,56,121,161,185,203,213],"action":[14,39,69],"performed":[15],"in":[16,55,68,79,184],"an":[17],"image.":[18],"An":[19],"may":[21,26,71],"contain":[22,72],"various":[23,80,156,199,220],"objects":[24],"that":[25,142],"be":[27,177],"associated":[28],"with":[29],"certain":[30],"actions;":[31],"responsible":[35],"to":[36,119,197,202,210],"translate":[37],"into":[40],"text":[41],"by":[42,155,179],"help":[44],"deep":[46,81,215],"learning":[47,82],"algorithms.":[48],"Image":[49],"challenging":[53],"task":[54],"field":[57],"processing":[60],"because":[61],"real":[62],"world":[63],"data":[64],"bit":[66],"complex":[67],"and":[70,103,116,137,151,168,206],"unidentified":[73],"objects.":[74],"It":[75],"has":[76],"been":[77],"implemented":[78,221],"algorithms":[83],"such":[84,111],"CNN":[86],"(Convolutional":[87],"Neural":[88,92,96],"Network),":[89,93,97],"RNN":[90],"(Recurrent":[91],"DNN":[94],"(Deep":[95],"LSTM":[98],"(Long":[99],"Short":[100],"Term":[101],"Memory)":[102],"many":[104,117],"more.":[105],"These":[106],"networks":[107],"use":[108],"distinct":[109],"datasets":[110],"Flickr8K,":[113],"Flickr30K,":[114],"MSCOCO":[115,138,145],"more":[118],"obtain":[120],"result":[122,159],"accordingly.":[123],"Flickr8K":[124],"contains":[125,133,139],"eight":[126],"thousand":[127,135],"images":[128,136,141],"for":[129],"training;":[130],"similarly":[131],"Flickr30K":[132],"thirty":[134],"82783":[140],"why":[144],"considered":[147],"large":[149],"dataset":[150],"it":[152,207],"preferred":[154],"researchers.":[157],"The":[158,171,191],"translation":[163,175],"based":[165],"on":[166],"syntactic":[167],"semantic":[169],"traits.":[170],"quality":[172],"can":[176],"measured":[178],"BLEU":[180],"(BiLingual":[181],"Evaluation":[182],"Understudy)":[183],"reference":[186],"ground":[188],"truth":[189],"captions.":[190],"intension":[192],"this":[194],"paper":[195],"review":[198],"approaches":[200],"related":[201],"also":[208],"intended":[209],"find":[211],"out":[212],"best":[214],"neural":[216],"network":[217],"model":[218],"among":[219],"models.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
