{"id":"https://openalex.org/W3134272453","doi":"https://doi.org/10.1109/tcsvt.2021.3063297","title":"Entity Slot Filling for Visual Captioning","display_name":"Entity Slot Filling for Visual Captioning","publication_year":2021,"publication_date":"2021-03-02","ids":{"openalex":"https://openalex.org/W3134272453","doi":"https://doi.org/10.1109/tcsvt.2021.3063297","mag":"3134272453"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3063297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3063297","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Bin","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091807843","display_name":"Yujuan Ding","orcid":"https://orcid.org/0000-0003-2945-1107"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yujuan Ding","raw_affiliation_strings":["Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hong Kong SAR","Laboratory for Artificial Intelligence in Design, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Laboratory for Artificial Intelligence in Design, Hong Kong SAR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061202217","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0002-6616-453X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063303076","display_name":"Liang Peng","orcid":"https://orcid.org/0000-0002-0576-1429"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","Institute of Electronics and Information Engineering of UESTC in Guangdong, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Electronics and Information Engineering of UESTC in Guangdong, Dongguan, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I4210110458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["School of Computing, the National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, the National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024408423"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":3.3017,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93536245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"52","last_page":"62"},"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":0.9954000115394592,"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":0.979200005531311,"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":0.9234247207641602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.831504225730896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6926486492156982},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6208492517471313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947802066802979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5909343361854553},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5746071338653564},{"id":"https://openalex.org/keywords/blank","display_name":"Blank","score":0.5424050688743591},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.436658650636673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3216897249221802},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2610703408718109}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9234247207641602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831504225730896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6926486492156982},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6208492517471313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947802066802979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5909343361854553},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5746071338653564},{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.5424050688743591},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.436658650636673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3216897249221802},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2610703408718109},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3063297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3063297","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1897761818","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123442489","https://openalex.org/W2130942839","https://openalex.org/W2133512280","https://openalex.org/W2143017621","https://openalex.org/W2154652894","https://openalex.org/W2170653751","https://openalex.org/W2171361956","https://openalex.org/W2184587602","https://openalex.org/W2194775991","https://openalex.org/W2202226326","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2516196286","https://openalex.org/W2550936021","https://openalex.org/W2575842049","https://openalex.org/W2605045867","https://openalex.org/W2619010992","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2766237723","https://openalex.org/W2784823820","https://openalex.org/W2795151422","https://openalex.org/W2884326683","https://openalex.org/W2887712318","https://openalex.org/W2887967003","https://openalex.org/W2890585349","https://openalex.org/W2896457183","https://openalex.org/W2914699769","https://openalex.org/W2946197666","https://openalex.org/W2949197413","https://openalex.org/W2955956881","https://openalex.org/W2962739339","https://openalex.org/W2962764817","https://openalex.org/W2962861647","https://openalex.org/W2962968835","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963717374","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2966715458","https://openalex.org/W2979987972","https://openalex.org/W2982553922","https://openalex.org/W2997591391","https://openalex.org/W3003735286","https://openalex.org/W3005971801","https://openalex.org/W3037773948","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3104486441","https://openalex.org/W3104802318","https://openalex.org/W4298033729","https://openalex.org/W4298392976","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6639118148","https://openalex.org/W6679436768","https://openalex.org/W6682086655","https://openalex.org/W6682631176","https://openalex.org/W6685230081","https://openalex.org/W6686463822","https://openalex.org/W6725318829","https://openalex.org/W6728439319","https://openalex.org/W6728881024","https://openalex.org/W6747826347","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6757380498","https://openalex.org/W6765766786","https://openalex.org/W6766904570","https://openalex.org/W6773096225","https://openalex.org/W6775970589"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2361638505","https://openalex.org/W2370352440","https://openalex.org/W2009954581","https://openalex.org/W3088136942","https://openalex.org/W4296141694","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W2379220204","https://openalex.org/W2005071119"],"abstract_inverted_index":{"To":[0,104],"explore":[1],"the":[2,7,11,35,69,75,83,101,106,140,144,149,190,208],"specific":[3],"visual":[4,84,94,195],"aspects":[5],"and":[6,50,96,111,133,175,180,194,205],"language":[8,48,57],"consistency":[9],"at":[10],"same":[12],"time,":[13],"this":[14],"paper":[15],"introduces":[16],"a":[17,61,154,160],"new":[18],"image":[19],"captioning":[20,28,117],"task,":[21,151],"dubbed":[22],"<italic":[23,119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[24,120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">entity":[25],"slot":[26,115],"filling":[27,116,200],"(ESFCap)</i>":[29],".":[30],"It":[31,182],"is":[32,183],"similar":[33],"to":[34,46,55,73,82,92,186,197],"masked":[36,135,145],"entity":[37,114],"completion":[38],"tasks":[39],"in":[40,98],"NLP,":[41],"which":[42],"are":[43],"widely":[44],"used":[45],"study":[47],"context":[49],"has":[51],"been":[52],"successfully":[53],"employed":[54],"improve":[56],"understanding.":[58],"Specifically,":[59],"given":[60],"sentence":[62,102],"with":[63,77,100,159],"blank":[64,76],"for":[65,143],"describing":[66],"an":[67,113],"image,":[68],"ESFCap":[70,107,150],"task":[71],"aims":[72],"fill":[74],"proper":[78],"text":[79,88,141],"content":[80],"according":[81],"information.":[85],"The":[86,126,168,202],"filled":[87],"should":[89],"be":[90],"grounded":[91],"correct":[93,199],"entities":[95],"also":[97,184],"concordance":[99],"structure.":[103],"support":[105],"research,":[108],"we":[109,152],"collect":[110],"release":[112],"dataset,":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Flickr30k-EnFi</i>":[121],",":[122],"based":[123],"on":[124,189],"Flickr30k-Entities.":[125],"Flickr30k-EnFi":[127],"dataset":[128],"consists":[129],"of":[130,210],"31,783":[131],"images":[132],"565,750":[134],"sentences,":[136],"as":[137,139],"well":[138],"snippets":[142],"slot.":[146],"For":[147],"tackling":[148],"propose":[153],"multi-modal":[155],"fusion":[156],"model":[157,170],"equipped":[158],"novel":[161],"adaptive":[162],"dynamic":[163],"attention":[164],"module,":[165],"termed":[166],"AdaMFN.":[167],"AdaMFN":[169],"effectively":[171],"leverages":[172],"both":[173],"global":[174],"local":[176],"information":[177],"from":[178],"vision":[179],"language.":[181],"able":[185],"adaptively":[187],"focus":[188],"key":[191],"linguistic":[192],"knowledge":[193],"regions":[196],"generate":[198],"results.":[201],"experimental":[203],"results":[204],"analysis":[206],"demonstrate":[207],"effectiveness":[209],"our":[211],"proposed":[212],"model.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}