{"id":"https://openalex.org/W3158091094","doi":"https://doi.org/10.1109/access.2021.3075579","title":"Text to Image Synthesis for Improved Image Captioning","display_name":"Text to Image Synthesis for Improved Image Captioning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3158091094","doi":"https://doi.org/10.1109/access.2021.3075579","mag":"3158091094"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3075579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3075579","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09416431.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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://ieeexplore.ieee.org/ielx7/6287639/9312710/09416431.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100681205","display_name":"Md Zakir Hossain","orcid":"https://orcid.org/0000-0002-9387-5767"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Md. Zakir Hossain","raw_affiliation_strings":["Discipline of Information Technology, Murdoch University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, Murdoch University, Perth, WA, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002219416","display_name":"Ferdous Sohel","orcid":"https://orcid.org/0000-0003-1557-4907"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ferdous Sohel","raw_affiliation_strings":["Discipline of Information Technology, Murdoch University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, Murdoch University, Perth, WA, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014927373","display_name":"Mohd Fairuz Shiratuddin","orcid":"https://orcid.org/0000-0002-9529-6320"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohd Fairuz Shiratuddin","raw_affiliation_strings":["Discipline of Information Technology, Murdoch University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, Murdoch University, Perth, WA, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002077138","display_name":"Hamid Laga","orcid":"https://orcid.org/0000-0002-4758-7510"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hamid Laga","raw_affiliation_strings":["Discipline of Information Technology, Murdoch University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, Murdoch University, Perth, WA, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100681205"],"corresponding_institution_ids":["https://openalex.org/I176790772"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.7581,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":{"value":0.96142472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"64918","last_page":"64928"},"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":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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":0.9772342443466187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8696921467781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6998111009597778},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6057329773902893},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5960561633110046},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.5632284879684448},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5461990237236023},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.45489826798439026},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4274861216545105},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4172837734222412},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38503068685531616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3829514980316162},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37988197803497314}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9772342443466187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696921467781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6998111009597778},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6057329773902893},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5960561633110046},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.5632284879684448},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5461990237236023},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.45489826798439026},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4274861216545105},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4172837734222412},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38503068685531616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3829514980316162},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37988197803497314},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2021.3075579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3075579","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09416431.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/9997812a-e111-4df8-a41d-61abb3bfce4c","is_oa":true,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/9997812a-e111-4df8-a41d-61abb3bfce4c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hossain, M Z, Sohel, F, Shiratuddin, M F, Laga, H & Bennamoun, M 2021, 'Text to Image Synthesis for Improved Image Captioning', IEEE Access, vol. 9, 9416431, pp. 64918 - 64928. https://doi.org/10.1109/ACCESS.2021.3075579","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:82755d92994745a78c1c6d30c2852db1","is_oa":true,"landing_page_url":"https://doaj.org/article/82755d92994745a78c1c6d30c2852db1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 9, Pp 64918-64928 (2021)","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/9997812a-e111-4df8-a41d-61abb3bfce4c","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85105047593&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hossain , M Z , Sohel , F , Shiratuddin , M F , Laga , H & Bennamoun , M 2021 , ' Text to Image Synthesis for Improved Image Captioning ' , IEEE Access , vol. 9 , 9416431 , pp. 64918 - 64928 . https://doi.org/10.1109/ACCESS.2021.3075579","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3075579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3075579","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09416431.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158091094.pdf","grobid_xml":"https://content.openalex.org/works/W3158091094.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W764651262","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2131774270","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2259424905","https://openalex.org/W2282219577","https://openalex.org/W2302086703","https://openalex.org/W2398118205","https://openalex.org/W2431874326","https://openalex.org/W2479423890","https://openalex.org/W2766993077","https://openalex.org/W2767577934","https://openalex.org/W2795061970","https://openalex.org/W2801271919","https://openalex.org/W2803525166","https://openalex.org/W2884211519","https://openalex.org/W2885013662","https://openalex.org/W2889031684","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2950212751","https://openalex.org/W2962835968","https://openalex.org/W2962845008","https://openalex.org/W2962968835","https://openalex.org/W2963163163","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963649796","https://openalex.org/W2963686907","https://openalex.org/W2963966654","https://openalex.org/W2964271185","https://openalex.org/W2978125519","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2990564716","https://openalex.org/W2991914565","https://openalex.org/W2998637494","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3100183449","https://openalex.org/W3100388886","https://openalex.org/W3101313921","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6745448612","https://openalex.org/W6753778666"],"related_works":["https://openalex.org/W3151908889","https://openalex.org/W2952673322","https://openalex.org/W2871882974","https://openalex.org/W2996202528","https://openalex.org/W4366260926","https://openalex.org/W2973208549","https://openalex.org/W2914998939","https://openalex.org/W2982558732","https://openalex.org/W4288087560","https://openalex.org/W4226253672"],"abstract_inverted_index":{"Generating":[0],"textual":[1],"descriptions":[2],"of":[3,19,48,128,152,161,174],"images":[4,35,60,119,186],"has":[5],"been":[6,26],"an":[7,73,108],"important":[8],"topic":[9],"in":[10],"computer":[11],"vision":[12],"and":[13,38,66,81,86,117,134,167],"natural":[14],"language":[15],"processing.":[16],"A":[17],"number":[18,47],"techniques":[20,32],"based":[21,97],"on":[22,28,114,137],"deep":[23],"learning":[24],"have":[25],"proposed":[27,154],"this":[29,69],"topic.":[30],"These":[31,42],"use":[33,91,107,184],"human-annotated":[34],"for":[36,84,164,178,187],"training":[37,49,85],"testing":[39,87],"the":[40,88,122,126,159,172,175],"models.":[41],"models":[43,130],"require":[44],"a":[45,92],"large":[46],"data":[50,83],"to":[51,99,102,120],"perform":[52],"at":[53],"their":[54],"full":[55],"potential.":[56],"Collecting":[57],"human":[58],"generated":[59,176],"with":[61],"associative":[62],"captions":[63,177],"is":[64],"expensive":[65],"time-consuming.":[67],"In":[68],"paper,":[70],"we":[71,183],"propose":[72],"image":[74,100,110,162],"captioning":[75,111,163],"method":[76,112],"that":[77,144],"uses":[78],"both":[79,115,132],"real":[80,116,179],"synthetic":[82,104,118,165],"model.":[89],"We":[90,106,124,142],"Generative":[93],"Adversarial":[94],"Network":[95],"(GAN)":[96],"text":[98],"generator":[101],"generate":[103,121],"images.":[105],"attention-based":[109],"trained":[113],"captions.":[123],"demonstrate":[125],"results":[127,147],"our":[129,145,153],"using":[131],"qualitative":[133],"quantitative":[135],"analysis":[136],"popularly":[138],"used":[139],"evaluation":[140],"metrics.":[141],"show":[143],"experimental":[146],"achieve":[148],"two":[149],"fold":[150],"benefits":[151],"work:":[155],"i)":[156],"it":[157,169],"demonstrates":[158],"effectiveness":[160],"images,":[166,180],"ii)":[168],"further":[170],"improves":[171],"quality":[173],"understandably":[181],"because":[182],"additional":[185],"training.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}