{"id":"https://openalex.org/W4387366606","doi":"https://doi.org/10.14569/ijacsa.2023.0140912","title":"Automatic Generation of Image Caption Based on Semantic Relation using Deep Visual Attention Prediction","display_name":"Automatic Generation of Image Caption Based on Semantic Relation using Deep Visual Attention Prediction","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387366606","doi":"https://doi.org/10.14569/ijacsa.2023.0140912"},"language":"en","primary_location":{"id":"doi:10.14569/ijacsa.2023.0140912","doi":"https://doi.org/10.14569/ijacsa.2023.0140912","is_oa":true,"landing_page_url":"https://doi.org/10.14569/ijacsa.2023.0140912","pdf_url":"http://thesai.org/Downloads/Volume14No9/Paper_12-Automatic_Generation_of_Image_Caption_Based_on_Semantic_Relation.pdf","source":{"id":"https://openalex.org/S23629721","display_name":"International Journal of Advanced Computer Science and Applications","issn_l":"2156-5570","issn":["2156-5570","2158-107X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310311819","host_organization_name":"Science and Information Organization","host_organization_lineage":["https://openalex.org/P4310311819"],"host_organization_lineage_names":["Science and Information Organization"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Advanced Computer Science and Applications","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://thesai.org/Downloads/Volume14No9/Paper_12-Automatic_Generation_of_Image_Caption_Based_on_Semantic_Relation.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062839054","display_name":"M. M. El-Gayar","orcid":"https://orcid.org/0000-0002-4644-1835","observed_orcids":["https://orcid.org/0000-0002-4644-1835"]},"institutions":[{"id":"https://openalex.org/I159247623","display_name":"Mansoura University","ror":"https://ror.org/01k8vtd75","country_code":"EG","type":"education","lineage":["https://openalex.org/I159247623"]},{"id":"https://openalex.org/I4388891815","display_name":"New Mansoura University","ror":"https://ror.org/05km0w312","country_code":"EG","type":"education","lineage":["https://openalex.org/I4388891815"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"M. M. EL-GAYAR","raw_affiliation_strings":["Department of Information Technology-Faculty of Computers and Information, Mansoura University Mansoura 35516, Egypt","Faculty of Computer Science and Engineering, New Mansoura University, New Mansoura, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology-Faculty of Computers and Information, Mansoura University Mansoura 35516, Egypt","institution_ids":["https://openalex.org/I159247623"]},{"raw_affiliation_string":"Faculty of Computer Science and Engineering, New Mansoura University, New Mansoura, Egypt","institution_ids":["https://openalex.org/I4388891815"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062839054"],"corresponding_institution_ids":["https://openalex.org/I159247623","https://openalex.org/I4388891815"],"apc_list":null,"apc_paid":null,"fwci":0.7235,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.67998644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"9","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":0.9940999746322632,"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":0.9940999746322632,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.002300000051036477,"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":0.0020000000949949026,"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":0.8650000095367432},{"id":"https://openalex.org/keywords/visual-attention","display_name":"visual attention","score":0.7839999794960022},{"id":"https://openalex.org/keywords/semantic-relations","display_name":"semantic relations","score":0.5329999923706055},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"discrete wavelet transform","score":0.9319999814033508},{"id":"https://openalex.org/keywords/multiscale-feature-extraction","display_name":"multi-scale feature extraction","score":0.8009999990463257},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.929585337638855},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8079506158828735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7213032245635986},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6767027378082275},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5106216073036194},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49796438217163086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.448112815618515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32967472076416016},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14569/ijacsa.2023.0140912","doi":"https://doi.org/10.14569/ijacsa.2023.0140912","is_oa":true,"landing_page_url":"https://doi.org/10.14569/ijacsa.2023.0140912","pdf_url":"http://thesai.org/Downloads/Volume14No9/Paper_12-Automatic_Generation_of_Image_Caption_Based_on_Semantic_Relation.pdf","source":{"id":"https://openalex.org/S23629721","display_name":"International Journal of Advanced Computer Science and Applications","issn_l":"2156-5570","issn":["2156-5570","2158-107X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310311819","host_organization_name":"Science and Information Organization","host_organization_lineage":["https://openalex.org/P4310311819"],"host_organization_lineage_names":["Science and Information Organization"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Advanced Computer Science and Applications","raw_type":"journal-article"},{"id":"pmh:oai:thesai.org:33de5d06-f337-470f-b410-3b182849ea68","doi":null,"is_oa":true,"landing_page_url":"https://thesai.org/Publications/ViewPaper?Volume=14&Issue=9&Code=IJACSA&SerialNo=12","pdf_url":"https://thesai.org/Downloads/Volume14No9/Paper_12-Automatic_Generation_of_Image_Caption_Based_on_Semantic_Relation.pdf","source":{"id":"https://openalex.org/S23629721","display_name":"International Journal of Advanced Computer Science and Applications","issn_l":"2156-5570","issn":["2156-5570","2158-107X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310311819","host_organization_name":"Science and Information Organization","host_organization_lineage":["https://openalex.org/P4310311819"],"host_organization_lineage_names":["Science and Information Organization"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Advanced Computer Science and Applications, Vol. 14, No. 9 (2023), ISSN 2158-107X","raw_type":"text"}],"best_oa_location":{"id":"doi:10.14569/ijacsa.2023.0140912","doi":"https://doi.org/10.14569/ijacsa.2023.0140912","is_oa":true,"landing_page_url":"https://doi.org/10.14569/ijacsa.2023.0140912","pdf_url":"http://thesai.org/Downloads/Volume14No9/Paper_12-Automatic_Generation_of_Image_Caption_Based_on_Semantic_Relation.pdf","source":{"id":"https://openalex.org/S23629721","display_name":"International Journal of Advanced Computer Science and Applications","issn_l":"2156-5570","issn":["2156-5570","2158-107X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-20","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310311819","host_organization_name":"Science and Information Organization","host_organization_lineage":["https://openalex.org/P4310311819"],"host_organization_lineage_names":["Science and Information Organization"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Advanced Computer Science and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387366606.pdf","grobid_xml":"https://content.openalex.org/works/W4387366606.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2161158373","https://openalex.org/W2176091656","https://openalex.org/W2481240925","https://openalex.org/W2560313346","https://openalex.org/W2745461083","https://openalex.org/W2784157037","https://openalex.org/W2890718122","https://openalex.org/W2938603906","https://openalex.org/W2961944450","https://openalex.org/W2964101993","https://openalex.org/W2974030101","https://openalex.org/W2995753487","https://openalex.org/W3006628257","https://openalex.org/W3010982166","https://openalex.org/W3014508564","https://openalex.org/W3015437081","https://openalex.org/W3018388102","https://openalex.org/W3023584964","https://openalex.org/W3045147787","https://openalex.org/W3091588028","https://openalex.org/W3094673569","https://openalex.org/W3137069976","https://openalex.org/W3161079477","https://openalex.org/W3165206901","https://openalex.org/W3216130706","https://openalex.org/W4213189167","https://openalex.org/W4220800343","https://openalex.org/W6600109629","https://openalex.org/W6779652526"],"related_works":["https://openalex.org/W4319594886","https://openalex.org/W4401751990","https://openalex.org/W2978125519","https://openalex.org/W7117109690","https://openalex.org/W2997252505","https://openalex.org/W6945130932","https://openalex.org/W4393859682","https://openalex.org/W3080813890","https://openalex.org/W7105736467","https://openalex.org/W7168146278"],"abstract_inverted_index":{"While":[0],"modern":[1],"systems":[2],"for":[3,30,135,236],"managing,":[4],"retrieving,":[5],"and":[6,45,118,132,158,176,202,216,228],"analyzing":[7],"images":[8],"heavily":[9],"rely":[10],"on":[11,167,171,195],"deriving":[12],"semantic":[13,165,173],"captions":[14],"to":[15,25,57,154,161],"categorize":[16],"images,":[17],"this":[18,70,189,240],"task":[19],"presents":[20,74],"a":[21,55,75,82,88,103,113,164,222,233],"considerable":[22],"challenge":[23],"due":[24],"the":[26,94,109,123,145,168,172,181,186],"extensive":[27],"capabilities":[28],"required":[29],"manual":[31],"processing,":[32],"particularly":[33],"with":[34,87,112,139],"large":[35],"images.":[36,100],"Despite":[37],"significant":[38,223],"advancements":[39],"in":[40,61,180,213,225,239],"automatic":[41],"image":[42,77,169,226],"caption":[43,166],"generation":[44],"human":[46],"attention":[47,59,134,137,229],"prediction":[48,116,230],"through":[49,64,192],"convolutional":[50,84,105],"neural":[51,85,106],"networks,":[52],"there":[53],"remains":[54],"need":[56],"enhance":[58],"models":[60],"these":[62],"networks":[63],"efficient":[65],"multi-scale":[66],"features":[67,98,141,178],"utilization.":[68],"Addressing":[69],"need,":[71],"our":[72],"study":[73],"novel":[76],"decoding":[78],"model":[79,117,160],"that":[80],"integrates":[81],"wavelet-driven":[83,104],"network":[86,107],"dual-stage":[89],"discrete":[90],"wavelet":[91],"transform,":[92],"enabling":[93],"extraction":[95],"of":[96,188],"salient":[97],"within":[99],"We":[101],"utilize":[102],"as":[108,122],"encoder,":[110],"coupled":[111],"deep":[114,126],"visual":[115,136],"Long":[119],"Short-Term":[120],"Memory":[121],"decoder.":[124],"The":[125,204],"Visual":[127],"Prediction":[128],"Model":[129],"calculates":[130],"channel":[131],"location":[133],"features,":[138],"local":[140],"assessed":[142],"by":[143],"considering":[144],"spatial-contextual":[146],"relationship":[147],"among":[148],"objects.":[149],"Our":[150],"primary":[151],"contribution":[152],"is":[153],"propose":[155],"an":[156],"encoder":[157],"decoder":[159],"automatically":[162],"create":[163],"based":[170],"contextual":[174],"information":[175],"spatial":[177],"present":[179],"image.":[182],"Also,":[183],"we":[184],"improved":[185],"performance":[187],"model,":[190],"demonstrated":[191],"experiments":[193],"conducted":[194],"three":[196],"widely":[197],"used":[198],"datasets:":[199],"Flickr8K,":[200],"Flickr30K,":[201],"MSCOCO.":[203],"proposed":[205],"approach":[206],"outperformed":[207],"current":[208],"methods,":[209],"achieving":[210],"superior":[211],"results":[212],"BLEU,":[214],"METEOR,":[215],"GLEU":[217],"scores.":[218],"This":[219],"research":[220],"offers":[221],"advancement":[224],"captioning":[227],"models,":[231],"presenting":[232],"promising":[234],"direction":[235],"future":[237],"work":[238],"field.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-10-06T00:00:00"}