{"id":"https://openalex.org/W3191818374","doi":"https://doi.org/10.24963/ijcai.2021/91","title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","display_name":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191818374","doi":"https://doi.org/10.24963/ijcai.2021/91","mag":"3191818374"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/91","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/91","pdf_url":"https://www.ijcai.org/proceedings/2021/0091.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0091.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078689432","display_name":"Zhihao Fan","orcid":"https://orcid.org/0000-0002-9910-7937"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Fan","raw_affiliation_strings":["Fudan University","Fudan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011504177","display_name":"Zhongyu Wei","orcid":"https://orcid.org/0000-0003-3789-8507"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":["Fudan University","Fudan University,","Research Institute of Intelligent and Complex Systems, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Research Institute of Intelligent and Complex Systems, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440548","display_name":"Siyuan Wang","orcid":"https://orcid.org/0000-0002-5036-0608"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["Fudan University","Fudan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002746311","display_name":"Ruize Wang","orcid":"https://orcid.org/0000-0001-6281-4091"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruize Wang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725946","display_name":"Zejun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejun Li","raw_affiliation_strings":["Fudan University","Fudan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103943513","display_name":"Haijun Shan","orcid":"https://orcid.org/0000-0001-5693-6084"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Shan","raw_affiliation_strings":["Zhejiang Lab","Fudan University,","Zhejiang Lab,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Zhejiang Lab,","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University","Fudan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University,","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078689432"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.2305,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89861201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"657","last_page":"663"},"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":0.9957000017166138,"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":0.9883999824523926,"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":0.9502989053726196},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.7527227401733398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216616272926331},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6033636927604675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5309659242630005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5084421038627625},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49933457374572754},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4651305079460144},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43686652183532715},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3599558472633362},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15746968984603882},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11885851621627808},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0896361768245697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06657630205154419}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9502989053726196},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.7527227401733398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216616272926331},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6033636927604675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5309659242630005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084421038627625},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49933457374572754},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4651305079460144},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43686652183532715},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3599558472633362},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15746968984603882},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11885851621627808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0896361768245697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06657630205154419},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/91","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/91","pdf_url":"https://www.ijcai.org/proceedings/2021/0091.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/91","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/91","pdf_url":"https://www.ijcai.org/proceedings/2021/0091.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3068989376","display_name":null,"funder_award_id":"21QA1400600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7064261960","display_name":null,"funder_award_id":"20dz1200600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191818374.pdf","grobid_xml":"https://content.openalex.org/works/W3191818374.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2150824314","https://openalex.org/W2302086703","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2558834163","https://openalex.org/W2607151106","https://openalex.org/W2745461083","https://openalex.org/W2808021740","https://openalex.org/W2949792119","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2983141445","https://openalex.org/W2984814708","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2996941455","https://openalex.org/W3034655362","https://openalex.org/W4288329833","https://openalex.org/W4289542422","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Existing":[0],"research":[1],"for":[2,68,87,113,133],"image":[3,8,69],"captioning":[4],"usually":[5],"represents":[6],"an":[7],"using":[9],"a":[10,31],"scene":[11,104],"graph":[12,105],"with":[13,60,144],"low-level":[14],"facts":[15],"(objects":[16],"and":[17,19,57,81,108,128,162],"relations)":[18],"fails":[20],"to":[21,43,64,101,124,140,165,182],"capture":[22],"the":[23,95,118,145,150,167,176],"high-level":[24,45],"semantics.":[25,47],"In":[26,48],"this":[27],"paper,":[28],"we":[29,50,83,152],"propose":[30,58,84],"Theme":[32,61],"Concepts":[33],"extended":[34],"Image":[35],"Captioning":[36],"(TCIC)":[37],"framework":[38],"that":[39,72],"incorporates":[40],"theme":[41,52,73,109,129,157],"concepts":[42,53,74,110,130,158],"represent":[44],"cross-modality":[46,168],"practice,":[49],"model":[51],"as":[54,111,131],"memory":[55],"vectors":[56,67],"Transformer":[59],"Nodes":[62],"(TTN)":[63],"incorporate":[65],"those":[66],"captioning.":[70],"Considering":[71],"can":[75],"be":[76],"learned":[77,159],"from":[78,160],"both":[79,103,126],"images":[80,161],"captions,":[82],"two":[85],"settings":[86,138],"their":[88],"representations":[89,155],"learning":[90],"based":[91,106],"on":[92,172],"TTN.":[93],"On":[94,117],"vision":[96],"side,":[97,120],"TTN":[98,121],"is":[99,122],"configured":[100,123],"take":[102,125],"features":[107],"input":[112,132],"visual":[114],"representation":[115,135],"learning.":[116,169],"language":[119],"captions":[127,143,164],"text":[134],"re-construction.":[136],"Both":[137],"aim":[139],"generate":[141],"target":[142],"same":[146],"transformer-based":[147],"decoder.":[148],"During":[149],"training,":[151],"further":[153],"align":[154],"of":[156,178],"corresponding":[163],"enforce":[166],"Experimental":[170],"results":[171],"MS":[173],"COCO":[174],"show":[175],"effectiveness":[177],"our":[179],"approach":[180],"compared":[181],"some":[183],"state-of-the-art":[184],"models.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}