{"id":"https://openalex.org/W3035404043","doi":"https://doi.org/10.1109/icme46284.2020.9102967","title":"Video Captioning With Temporal And Region Graph Convolution Network","display_name":"Video Captioning With Temporal And Region Graph Convolution Network","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3035404043","doi":"https://doi.org/10.1109/icme46284.2020.9102967","mag":"3035404043"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Video_captioning_with_temporal_and_region_graph_convolution_network/20695126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112540850","display_name":"Xinlong Xiao","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":true,"raw_author_name":"Xinlong Xiao","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"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":"Yuejie Zhang","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"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":"Rui Feng","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375722","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7561-0143"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["School of Information Managerment and Engineering, Shanghai University of Finance and Econnomics, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Managerment and Engineering, Shanghai University of Finance and Econnomics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008929449","display_name":"Shang Gao","orcid":"https://orcid.org/0000-0002-2947-7780"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shang Gao","raw_affiliation_strings":["School of Information Technology, Deakin University, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Victoria, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075964389","display_name":"Weiguo Fan","orcid":"https://orcid.org/0000-0003-1272-5538"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiguo Fan","raw_affiliation_strings":["Department of Business Analytics, University of Iowa, Iowa, USA"],"affiliations":[{"raw_affiliation_string":"Department of Business Analytics, University of Iowa, Iowa, USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112540850"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.4906,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65588991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8470067977905273},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7475972175598145},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7235723733901978},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6603518724441528},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6384005546569824},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5540274977684021},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5362303853034973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46991291642189026},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.422894686460495},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2801932096481323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1512572169303894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10731306672096252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470067977905273},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7475972175598145},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7235723733901978},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6603518724441528},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6384005546569824},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5540274977684021},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5362303853034973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46991291642189026},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.422894686460495},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2801932096481323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1512572169303894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10731306672096252},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme46284.2020.9102967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30140839","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/20695126","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Video_captioning_with_temporal_and_region_graph_convolution_network/20695126","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20695126","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Video_captioning_with_temporal_and_region_graph_convolution_network/20695126","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2765658575","https://openalex.org/W2806331055","https://openalex.org/W2807834696","https://openalex.org/W2890531016","https://openalex.org/W2904698318","https://openalex.org/W2905145027","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2963552819","https://openalex.org/W2964015378","https://openalex.org/W6684090549","https://openalex.org/W6726873649"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W2149051193"],"abstract_inverted_index":{"Video":[0],"captioning":[1,38],"aims":[2],"to":[3,31,69,86],"generate":[4],"a":[5,10,35,95,106,111],"natural":[6],"language":[7],"description":[8],"for":[9,98,114],"given":[11],"video":[12,37],"clip":[13],"that":[14,60],"includes":[15],"not":[16],"only":[17],"spatial":[18],"information":[19,29,57,92],"but":[20],"also":[21,103],"temporal":[22],"information.":[23,101],"To":[24],"better":[25],"exploit":[26],"such":[27],"spatial-temporal":[28],"attached":[30],"videos,":[32],"we":[33,80],"propose":[34],"novel":[36],"framework":[39],"with":[40,89,110],"Temporal":[41],"Graph":[42,47,82],"Network":[43,48,84],"(TGN)":[44],"and":[45,93,126],"Region":[46],"(RGN).":[49],"TGN":[50],"mainly":[51],"focuses":[52],"on":[53,121],"utilizing":[54,99],"the":[55,71,129],"sequential":[56,91],"of":[58,62,131],"frames":[59,88],"most":[61],"existing":[63],"methods":[64],"ignore.":[65],"RGN":[66],"is":[67],"designed":[68],"explore":[70],"relationships":[72],"among":[73],"salient":[74],"objects.":[75],"Different":[76],"from":[77],"previous":[78],"work,":[79],"introduce":[81],"Convolution":[83],"(GCN)":[85],"encode":[87],"their":[90],"build":[94],"region":[96],"graph":[97],"object":[100],"We":[102],"particularly":[104],"adopt":[105],"stack":[107],"GRU":[108],"decoder":[109],"coarse-to-fine":[112],"structure":[113],"caption":[115],"generation.":[116],"Very":[117],"promising":[118],"experimental":[119],"results":[120],"two":[122],"benchmark":[123],"datasets":[124],"(MSVD":[125],"MSR-VTT)":[127],"show":[128],"effectiveness":[130],"our":[132],"model.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}