{"id":"https://openalex.org/W3158984727","doi":"https://doi.org/10.1109/ciss50987.2021.9400209","title":"Facilitated Deep Learning Models for Image Captioning","display_name":"Facilitated Deep Learning Models for Image Captioning","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3158984727","doi":"https://doi.org/10.1109/ciss50987.2021.9400209","mag":"3158984727"},"language":"en","primary_location":{"id":"doi:10.1109/ciss50987.2021.9400209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012916550","display_name":"Imtinan Azhar","orcid":null},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Imtinan Azhar","raw_affiliation_strings":["University of Sharjah, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000538231","display_name":"Imad Afyouni","orcid":"https://orcid.org/0000-0001-6686-3069"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Imad Afyouni","raw_affiliation_strings":["University of Sharjah, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069884464","display_name":"Ashraf Elnagar","orcid":"https://orcid.org/0000-0003-2265-7268"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ashraf Elnagar","raw_affiliation_strings":["University of Sharjah, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29891158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9904999732971191,"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":0.9851999878883362,"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":0.9751953482627869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8536122441291809},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7256136536598206},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7082573175430298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6742113828659058},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5600961446762085},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5076128244400024},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5033037066459656},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4998812675476074},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47856858372688293},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4388582408428192},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43053358793258667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40994635224342346},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4083249270915985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32255953550338745}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9751953482627869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8536122441291809},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7256136536598206},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7082573175430298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6742113828659058},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5600961446762085},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5076128244400024},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5033037066459656},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4998812675476074},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47856858372688293},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4388582408428192},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43053358793258667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40994635224342346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4083249270915985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32255953550338745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss50987.2021.9400209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1969616664","https://openalex.org/W2130942839","https://openalex.org/W2803206166","https://openalex.org/W2884367402","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2945436491","https://openalex.org/W2963403868","https://openalex.org/W2963630207","https://openalex.org/W2986670728","https://openalex.org/W3005875885","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6679436768","https://openalex.org/W6714414533","https://openalex.org/W6739901393","https://openalex.org/W6752113587","https://openalex.org/W6754778999"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"This":[0,89],"paper":[1,103],"focuses":[2],"on":[3,131,139],"developing":[4,26],"semantic":[5,116,154],"image":[6,12,23,40,69,77],"caption":[7,87,117],"generation":[8],"techniques":[9],"that":[10,110],"leverage":[11],"and":[13,32,49,79,96,129,133,136,161,176,185,191,194,201],"scene":[14],"understanding.":[15],"More":[16],"particularly,":[17],"we":[18],"are":[19,122,127],"interested":[20],"in":[21,170,179,192],"addressing":[22],"captioning":[24,70],"by":[25,71,81],"a":[27,42,107,140,153,171],"mixture":[28],"of":[29,54,101,125,142,146,174],"object":[30],"detection":[31],"attention-enriched":[33],"deep":[34],"learning":[35],"models.":[36],"To":[37],"extract":[38],"the":[39,65,76,147,158,162],"features,":[41],"Convolutional":[43],"Neural":[44,56],"Network":[45],"(CNN)":[46],"is":[47,61,104],"used,":[48],"then":[50,80,137],"an":[51,83],"extended":[52],"version":[53],"Recurrent":[55],"Networks":[57],"(LSTM)":[58],"with":[59],"attention-enrichment":[60],"adopted":[62],"to":[63,105],"generate":[64],"caption.":[66],"We":[67],"implement":[68],"considering":[72],"detected":[73],"objects":[74],"from":[75,94,188,198],"scene,":[78],"integrating":[82],"attention":[84],"mechanism":[85],"for":[86,115],"generation.":[88,118],"can":[90],"have":[91],"multiple":[92],"advantages":[93],"accuracy":[95],"semantics":[97],"perspectives.":[98],"The":[99],"objective":[100],"this":[102],"introduce":[106],"combined":[108],"pipeline":[109],"employs":[111],"several":[112],"variant":[113,120],"models":[114,121,149],"Four":[119],"proposed,":[123],"all":[124],"them":[126],"implemented":[128],"trained":[130],"COCO":[132,143],"Flickr30k":[134],"datasets,":[135],"tested":[138],"subset":[141],"dataset.":[144],"Results":[145],"different":[148],"were":[150],"evaluated":[151],"using":[152],"similarity":[155],"analysis":[156],"between":[157],"generated":[159],"captions":[160],"actual":[163],"ground":[164],"truth":[165],"captions.":[166],"Our":[167],"framework":[168],"helps":[169],"deeper":[172],"understanding":[173],"images":[175,197],"decision":[177],"making":[178],"diverse":[180],"use-cases":[181],"such":[182],"as":[183],"innovative":[184],"distinctive":[186],"responses":[187],"multimodal":[189],"data,":[190],"analyzing":[193],"monitoring":[195],"crowdsourced":[196],"social":[199],"media":[200],"other":[202],"sources.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}