{"id":"https://openalex.org/W3163971663","doi":"https://doi.org/10.1109/tcsvt.2021.3058626","title":"Stacked Multimodal Attention Network for Context-Aware Video Captioning","display_name":"Stacked Multimodal Attention Network for Context-Aware Video Captioning","publication_year":2021,"publication_date":"2021-12-23","ids":{"openalex":"https://openalex.org/W3163971663","doi":"https://doi.org/10.1109/tcsvt.2021.3058626","mag":"3163971663"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3058626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3058626","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/A5101675150","display_name":"Yi Zheng","orcid":"https://orcid.org/0000-0001-5547-0956"},"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":"Yi Zheng","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5547-0956","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, 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":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7993-7223","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, 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":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, 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":["Shanghai Key Laboratory of Financial Information Technology, School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7561-0143","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Financial Information Technology, School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"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, Tippie College of Business, The University of Iowa, Iowa City, IA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1272-5538","affiliations":[{"raw_affiliation_string":"Department of Business Analytics, Tippie College of Business, The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9208,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.92558402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"31","last_page":"42"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9965000152587891,"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":0.9627701044082642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7769245505332947},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7122689485549927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5407405495643616},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5276797413825989},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5024189949035645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43485406041145325},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43166863918304443},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43151938915252686},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4165460765361786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37820228934288025},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2412545084953308},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1445232629776001}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9627701044082642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769245505332947},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7122689485549927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407405495643616},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5276797413825989},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5024189949035645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43485406041145325},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43166863918304443},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43151938915252686},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4165460765361786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37820228934288025},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2412545084953308},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1445232629776001},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3058626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3058626","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G2372857774","display_name":null,"funder_award_id":"61976057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G292109295","display_name":"\u878d\u5408\u591a\u6a21\u6001\u6587\u672c\u5173\u8054\u5206\u6790\u4e0e\u6316\u6398\u7684\u8de8\u5a92\u4f53\u793e\u4f1a\u56fe\u50cf\u68c0\u7d22\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61572140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5101276346","display_name":null,"funder_award_id":"19ZR1417200","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G6770253380","display_name":null,"funder_award_id":"19YJA630116","funder_id":"https://openalex.org/F4320335982","funder_display_name":"Humanities and Social Science Fund of Ministry of Education of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335982","display_name":"Humanities and Social Science Fund of Ministry of Education of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W877909479","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W1956340063","https://openalex.org/W2005227457","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2425121537","https://openalex.org/W2506483933","https://openalex.org/W2507365558","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2549139847","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2619947201","https://openalex.org/W2621571501","https://openalex.org/W2739107216","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2765658575","https://openalex.org/W2807834696","https://openalex.org/W2808071176","https://openalex.org/W2887585070","https://openalex.org/W2895845501","https://openalex.org/W2901988662","https://openalex.org/W2904698318","https://openalex.org/W2905145027","https://openalex.org/W2962681491","https://openalex.org/W2962907269","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963552819","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2964896648","https://openalex.org/W2965359408","https://openalex.org/W2970768710","https://openalex.org/W2981411942","https://openalex.org/W2984862483","https://openalex.org/W2986670728","https://openalex.org/W3034221024","https://openalex.org/W3034593503","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3105136412","https://openalex.org/W6640212811","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6754140808","https://openalex.org/W6780226713","https://openalex.org/W6955071965"],"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/W4289422896"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"models":[2],"for":[3],"video":[4,26,60],"captioning":[5,61],"usually":[6],"employ":[7],"an":[8],"attention-based":[9],"encoder-decoder":[10],"framework.":[11,132],"However,":[12],"current":[13,49],"approaches":[14],"mainly":[15],"attend":[16],"to":[17,87,102],"the":[18,25,29,33,94,105,114,126],"motion":[19],"features":[20,23,90],"and":[21,42,73,92,98,110,121,128],"object":[22],"of":[24,117,130],"when":[27],"generating":[28],"caption,":[30],"but":[31,35],"ignore":[32],"potential":[34],"useful":[36],"historical":[37,75],"information.":[38],"Besides,":[39],"exposure":[40],"bias":[41],"vanishing":[43],"gradients":[44],"problems":[45],"always":[46],"exist":[47],"in":[48],"caption":[50,78],"generation":[51,79],"models.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"a":[58,84],"novel":[59],"framework,":[62],"named":[63],"Stacked":[64],"Multimodal":[65],"Attention":[66],"Network":[67],"(SMAN).":[68],"It":[69],"adopts":[70],"additional":[71],"visual":[72],"textual":[74],"information":[76],"during":[77],"as":[80],"context":[81],"features,":[82],"employs":[83],"stacked":[85],"architecture":[86],"process":[88],"different":[89],"gradually,":[91],"utilizes":[93],"Reinforcement":[95],"Learning":[96],"method":[97],"coarse-to-fine":[99],"training":[100],"strategy":[101],"further":[103],"improve":[104],"generated":[106],"results.":[107],"Both":[108],"quantitative":[109],"qualitative":[111],"experiments":[112],"on":[113,137],"benchmark":[115],"datasets":[116],"<italic":[118,122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[119,123,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MSVD</i>":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MSR-VTT</i>":[124],"show":[125],"effectiveness":[127],"feasibility":[129],"our":[131],"The":[133],"codes":[134],"are":[135],"available":[136],"<uri":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zhengyi123456/SMAN</uri>":[140],".":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
