{"id":"https://openalex.org/W3165206901","doi":"https://doi.org/10.23919/fruct52173.2021.9435534","title":"Deep Image Captioning Survey: A Resource Availability Perspective","display_name":"Deep Image Captioning Survey: A Resource Availability Perspective","publication_year":2021,"publication_date":"2021-05-12","ids":{"openalex":"https://openalex.org/W3165206901","doi":"https://doi.org/10.23919/fruct52173.2021.9435534","mag":"3165206901"},"language":"en","primary_location":{"id":"doi:10.23919/fruct52173.2021.9435534","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fruct52173.2021.9435534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th Conference of Open Innovations Association (FRUCT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doaj.org/article/6a5bacc845734bbb936edba9e8d85305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038532823","display_name":"Mousa Al Sulaimi","orcid":null},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":true,"raw_author_name":"Mousa Al Sulaimi","raw_affiliation_strings":["Kuwait University, Kuwait"],"affiliations":[{"raw_affiliation_string":"Kuwait University, Kuwait","institution_ids":["https://openalex.org/I36721946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077897203","display_name":"Imtiaz Ahmad","orcid":"https://orcid.org/0000-0002-0673-7324"},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Imtiaz Ahmad","raw_affiliation_strings":["Kuwait University, Kuwait"],"affiliations":[{"raw_affiliation_string":"Kuwait University, Kuwait","institution_ids":["https://openalex.org/I36721946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028271141","display_name":"Mohammad Jeragh","orcid":"https://orcid.org/0000-0002-1979-9997"},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Mohammad Jeragh","raw_affiliation_strings":["Kuwait University, Kuwait"],"affiliations":[{"raw_affiliation_string":"Kuwait University, Kuwait","institution_ids":["https://openalex.org/I36721946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038532823"],"corresponding_institution_ids":["https://openalex.org/I36721946"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47034314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"13"},"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":0.9972000122070312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9956318140029907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773964524269104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6486541628837585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6143026947975159},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5946990251541138},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5241475701332092},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5209839940071106},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4437423646450043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4246048927307129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3628867566585541},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06800073385238647}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9956318140029907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773964524269104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6486541628837585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6143026947975159},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5946990251541138},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5241475701332092},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5209839940071106},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4437423646450043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4246048927307129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3628867566585541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06800073385238647},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/fruct52173.2021.9435534","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fruct52173.2021.9435534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th Conference of Open Innovations Association (FRUCT)","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:6a5bacc845734bbb936edba9e8d85305","is_oa":true,"landing_page_url":"https://doaj.org/article/6a5bacc845734bbb936edba9e8d85305","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":"Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 29, Iss 1, Pp 3-13 (2021)","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:doaj.org/article:6a5bacc845734bbb936edba9e8d85305","is_oa":true,"landing_page_url":"https://doaj.org/article/6a5bacc845734bbb936edba9e8d85305","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":"Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 29, Iss 1, Pp 3-13 (2021)","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W2082453965","https://openalex.org/W2133564696","https://openalex.org/W2282219577","https://openalex.org/W2533598788","https://openalex.org/W2546938941","https://openalex.org/W2604178507","https://openalex.org/W2618530766","https://openalex.org/W2749708282","https://openalex.org/W2753215597","https://openalex.org/W2767577934","https://openalex.org/W2767780846","https://openalex.org/W2803259101","https://openalex.org/W2805954242","https://openalex.org/W2808503835","https://openalex.org/W2890718122","https://openalex.org/W2893724244","https://openalex.org/W2896348597","https://openalex.org/W2945436491","https://openalex.org/W2962968835","https://openalex.org/W2963048642","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963743213","https://openalex.org/W2963992143","https://openalex.org/W2967223102","https://openalex.org/W2970327218","https://openalex.org/W2981994675","https://openalex.org/W2990307191","https://openalex.org/W2992478697","https://openalex.org/W3034493371","https://openalex.org/W3102566412","https://openalex.org/W3103211586","https://openalex.org/W4320013936","https://openalex.org/W4322614756","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6639657675","https://openalex.org/W6679434410","https://openalex.org/W6730084236","https://openalex.org/W6749381284","https://openalex.org/W6749667189","https://openalex.org/W6752865951","https://openalex.org/W6756893277","https://openalex.org/W6762747416","https://openalex.org/W6763871817"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W2990774877"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,28,37,77],"deep":[3,21,84],"learning":[4,85],"have":[5,24,34],"enabled":[6],"machines":[7,23],"to":[8,93],"see,":[9],"hear,":[10],"and":[11,50,106,111,127,157,172],"even":[12],"speak.":[13],"In":[14],"some":[15,132],"cases,":[16],"with":[17,123,137,145],"the":[18,74,99,114,165],"help":[19],"of":[20,73,151,176],"learning,":[22],"also":[25,162],"outperformed":[26],"humans":[27],"these":[29],"complex":[30],"tasks.":[31],"Such":[32],"improvements":[33],"reignited":[35],"interest":[36],"many":[38],"fields.":[39],"Image":[40],"captioning,":[41,160],"which":[42],"is":[43,80],"considered":[44],"an":[45],"intersection":[46],"between":[47],"computer":[48],"vision":[49],"natural":[51],"language":[52],"processing,":[53],"has":[54,91],"recently":[55],"received":[56],"significant":[57],"attention.":[58],"Deep":[59],"learning-based":[60],"image":[61,78,89,108,159,177],"captioning":[62,79,90,109],"models":[63],"represent":[64],"a":[65,168],"great":[66],"improvement":[67],"on":[68,82,104,170],"traditional":[69],"methods.":[70,86,112],"However,":[71],"most":[72],"work":[75],"done":[76],"based":[81],"supervised":[83],"Recently,":[87],"unsupervised":[88,105],"started":[92],"gather":[94],"momentum.":[95],"This":[96],"paper":[97],"presents":[98,167],"first":[100],"survey":[101,115,166],"that":[102],"focuses":[103],"semi-supervised":[107],"techniques":[110],"Additionally,":[113],"shows":[116],"how":[117],"such":[118,154],"methods":[119,133],"can":[120,134,142],"be":[121,135,143],"used":[122,136,144],"different":[124],"data":[125,128],"availability":[126],"pairing":[129],"settings,":[130],"where":[131],"paired":[138],"data,":[139,153],"while":[140],"others":[141],"unpaired":[146,152],"data.":[147],"Furthermore,":[148],"special":[149],"cases":[150],"as":[155],"cross-domain":[156],"cross-lingual":[158],"are":[161],"discussed.":[163],"Finally,":[164],"discussion":[169],"challenges":[171],"future":[173],"research":[174],"directions":[175],"captioning.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}