{"id":"https://openalex.org/W2997651548","doi":"https://doi.org/10.1109/icis46139.2019.8940218","title":"Slot based Image Captioning with WGAN","display_name":"Slot based Image Captioning with WGAN","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2997651548","doi":"https://doi.org/10.1109/icis46139.2019.8940218","mag":"2997651548"},"language":"en","primary_location":{"id":"doi:10.1109/icis46139.2019.8940218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis46139.2019.8940218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"},"type":"article","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/A5078021087","display_name":"Ziyu Xue","orcid":"https://orcid.org/0000-0001-7035-7089"},"institutions":[{"id":"https://openalex.org/I4210111085","display_name":"Academy of Broadcasting Science","ror":"https://ror.org/01z4nez64","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210111085"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Xue","raw_affiliation_strings":["Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China","institution_ids":["https://openalex.org/I4210111085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435848","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-0961-0441"},"institutions":[{"id":"https://openalex.org/I4210111085","display_name":"Academy of Broadcasting Science","ror":"https://ror.org/01z4nez64","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210111085"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China","institution_ids":["https://openalex.org/I4210111085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100304377","display_name":"Peiyu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111085","display_name":"Academy of Broadcasting Science","ror":"https://ror.org/01z4nez64","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210111085"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyu Guo","raw_affiliation_strings":["Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Security Technology Institute, Academy of Broadcasting Science, NRTA, Beijing, China","institution_ids":["https://openalex.org/I4210111085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.15710079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2019","issue":null,"first_page":"241","last_page":"246"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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":0.9764866828918457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8217809200286865},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7378779649734497},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6663203835487366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5846155881881714},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5748894214630127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5300533175468445},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5137263536453247},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5097076892852783},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.46718552708625793},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4661693871021271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4104779362678528},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.22619739174842834}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9764866828918457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217809200286865},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7378779649734497},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6663203835487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846155881881714},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5748894214630127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5300533175468445},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5137263536453247},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5097076892852783},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.46718552708625793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4661693871021271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4104779362678528},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.22619739174842834},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icis46139.2019.8940218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis46139.2019.8940218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"},{"id":"mag:3091787902","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002213547145129","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1527575280","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/W1969616664","https://openalex.org/W2008056655","https://openalex.org/W2036879845","https://openalex.org/W2115613106","https://openalex.org/W2143238378","https://openalex.org/W2150806568","https://openalex.org/W2159243025","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2549599535","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2601748485","https://openalex.org/W2605045867","https://openalex.org/W2611009517","https://openalex.org/W2770251894","https://openalex.org/W2795151422","https://openalex.org/W2951183276","https://openalex.org/W2951684117","https://openalex.org/W2962706528","https://openalex.org/W2962968835","https://openalex.org/W2963576560","https://openalex.org/W2963745697","https://openalex.org/W2964049455","https://openalex.org/W2964241990","https://openalex.org/W3104379732","https://openalex.org/W4230872509","https://openalex.org/W6630875275","https://openalex.org/W6638742206","https://openalex.org/W6729046916"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750"],"abstract_inverted_index":{"Existing":[0],"image":[1,30,105],"captioning":[2,31,106,110],"methods":[3],"are":[4,63,88],"always":[5],"limited":[6],"to":[7],"the":[8,60,114],"rules":[9],"of":[10,76,116],"words":[11],"or":[12],"syntax":[13],"with":[14,38,49],"single":[15],"sentence":[16,47,79,84],"and":[17,81,98,100,107],"poor":[18],"words.":[19],"In":[20],"this":[21,23],"paper,":[22],"paper":[24],"introduces":[25],"a":[26,46,77,82],"novel":[27,108],"framework":[28],"for":[29],"tasks":[32,111],"which":[33,62],"reconciles":[34],"slot":[35,51],"filling":[36],"approaches":[37],"neural":[39],"network":[40],"approaches.":[41],"Our":[42,73],"approach":[43],"first":[44],"generates":[45],"template":[48],"many":[50],"locations":[52],"using":[53],"Wasserstein":[54],"Generative":[55],"Adversarial":[56],"Network":[57],"(WGAN).":[58],"Then":[59],"slots":[61],"in":[64],"visual":[65],"regions":[66],"will":[67],"be":[68],"filled":[69],"by":[70],"object":[71,109],"detectors.":[72],"model":[74],"consists":[75],"structured":[78],"generator":[80],"multi-level":[83],"discriminator.":[85],"Extensive":[86],"experiments":[87],"conducted":[89],"on":[90,103],"three":[91],"benchmark":[92],"datasets,":[93],"(i.e.,":[94],"Microsoft":[95],"COCO,":[96],"Flickr8k":[97],"Flickr30k),":[99],"experimental":[101],"results":[102],"standard":[104],"clearly":[112],"corroborate":[113],"efficacy":[115],"our":[117],"method.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}