{"id":"https://openalex.org/W4285200050","doi":"https://doi.org/10.1109/tmm.2022.3183402","title":"Contextual Attention Network for Emotional Video Captioning","display_name":"Contextual Attention Network for Emotional Video Captioning","publication_year":2022,"publication_date":"2022-06-15","ids":{"openalex":"https://openalex.org/W4285200050","doi":"https://doi.org/10.1109/tmm.2022.3183402"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3183402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3183402","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5015177224","display_name":"Peipei Song","orcid":"https://orcid.org/0000-0001-6764-3375"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peipei Song","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Beijing, China","Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data (HFUT), Ministry of Education and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015177224"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":3.0565,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92786434,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"1858","last_page":"1867"},"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":0.9984999895095825,"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":0.996399998664856,"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":0.8267279267311096},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.6606980562210083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5460006594657898},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5138450264930725},{"id":"https://openalex.org/keywords/deixis","display_name":"Deixis","score":0.4849017262458801},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44979265332221985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4480651617050171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.389210045337677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.231190025806427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18781980872154236},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17101266980171204},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11461570858955383}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8267279267311096},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6606980562210083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5460006594657898},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5138450264930725},{"id":"https://openalex.org/C13077596","wikidata":"https://www.wikidata.org/wiki/Q340015","display_name":"Deixis","level":2,"score":0.4849017262458801},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44979265332221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480651617050171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.389210045337677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.231190025806427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18781980872154236},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17101266980171204},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11461570858955383},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3183402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3183402","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5232388117","display_name":null,"funder_award_id":"61725203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5353501536","display_name":null,"funder_award_id":"61876058","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8446091004","display_name":null,"funder_award_id":"JZ2020HGTB0020","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2081835714","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2110933980","https://openalex.org/W2116001771","https://openalex.org/W2133459682","https://openalex.org/W2134860945","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2156709807","https://openalex.org/W2164290393","https://openalex.org/W2188687388","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2339620988","https://openalex.org/W2619947201","https://openalex.org/W2625940279","https://openalex.org/W2766375149","https://openalex.org/W2786399470","https://openalex.org/W2807834696","https://openalex.org/W2822349497","https://openalex.org/W2905145027","https://openalex.org/W2954199749","https://openalex.org/W2955956881","https://openalex.org/W2962681491","https://openalex.org/W2962907269","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2963062932","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2964067226","https://openalex.org/W2964241990","https://openalex.org/W2984862483","https://openalex.org/W2990818246","https://openalex.org/W2996799978","https://openalex.org/W3034493371","https://openalex.org/W3034624317","https://openalex.org/W3035365026","https://openalex.org/W3093026747","https://openalex.org/W3131477521","https://openalex.org/W3176425931","https://openalex.org/W3182328899","https://openalex.org/W3187313248","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6682691769","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6748197246","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W1429031248","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"an":[3],"emerging":[4],"and":[5,46,50,70,77,113,141,153,158,169],"challenging":[6],"task\u2014emotional":[7],"video":[8,54,76,157,164],"captioning.":[9,95],"Formally,":[10],"given":[11],"a":[12,38],"video,":[13,26],"the":[14,21,25,30,34,48,53,84,98,102,129,132,172,178],"task":[15],"aims":[16],"to":[17,87,90,135,138,177],"not":[18],"only":[19],"describe":[20],"factual":[22],"content":[23],"of":[24,105,131,156,174],"but":[27],"also":[28],"discover":[29],"emotional":[31,163],"clues":[32],"in":[33,52],"video.":[35],"We":[36,96],"propose":[37],"novel":[39],"Contextual":[40],"Attention":[41],"Network":[42],"(CANet),":[43],"which":[44],"recognizes":[45],"describes":[47],"fact":[49],"emotion":[51],"by":[55],"semantic-rich":[56],"context":[57],"learning.":[58],"To":[59],"be":[60,136],"specific,":[61],"at":[62],"each":[63],"time":[64],"step,":[65],"we":[66,82],"first":[67],"extract":[68],"visual":[69],"textual":[71],"features":[72,89],"from":[73,151],"both":[74],"input":[75],"previously":[78],"generated":[79,133],"words.":[80],"Then,":[81],"apply":[83],"attention":[85],"mechanism":[86],"these":[88],"capture":[91],"informative":[92],"contexts":[93],"for":[94],"train":[97],"CANet":[99,175],"model":[100],"with":[101],"joint":[103],"optimization":[104],"cross-entropy":[106],"loss":[107,115],"<inline-formula":[108,116,123,142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[109,117,124,143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[110,118,125,144],"notation=\"LaTeX\">$\\mathcal":[111,119,126,145],"{L}_{CE}$</tex-math></inline-formula>":[112,127],"contrastive":[114],"{L}_{CL}$</tex-math></inline-formula>":[120,146],",":[121],"where":[122],"constrains":[128],"semantics":[130],"sentence":[134],"close":[137],"human":[139],"annotation":[140],"encourages":[147],"discriminative":[148],"representation":[149],"learning":[150],"positive":[152],"negative":[154],"pairs":[155],"caption.":[159],"Experiments":[160],"on":[161],"two":[162],"captioning":[165],"datasets":[166],"(i.e.,":[167],"EmVidCap":[168],"EmVidCap-S)":[170],"demonstrate":[171],"superiority":[173],"compared":[176],"state-of-the-art":[179],"approaches.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}