{"id":"https://openalex.org/W3207461616","doi":"https://doi.org/10.1109/icme52920.2022.9859743","title":"Visual-Aware Attention Dual-Stream Decoder for Video Captioning","display_name":"Visual-Aware Attention Dual-Stream Decoder for Video Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3207461616","doi":"https://doi.org/10.1109/icme52920.2022.9859743","mag":"3207461616"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101456842","display_name":"Zhixin Sun","orcid":"https://orcid.org/0000-0001-6148-9688"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Sun","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736130","display_name":"Shuqin Chen","orcid":"https://orcid.org/0000-0003-3436-653X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Chen","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113156659","display_name":"Luo Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Zhong","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.2774,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57397734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9972000122070312,"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":0.9965999722480774,"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":0.9344715476036072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8629454374313354},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7317267060279846},{"id":"https://openalex.org/keywords/rapid-serial-visual-presentation","display_name":"Rapid serial visual presentation","score":0.6568231582641602},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.505610466003418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4921087622642517},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.4693900942802429},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4674350321292877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44770103693008423},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4251404404640198},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42248696088790894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35606348514556885},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16679376363754272},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.11549657583236694}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9344715476036072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629454374313354},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7317267060279846},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.6568231582641602},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.505610466003418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921087622642517},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.4693900942802429},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4674350321292877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44770103693008423},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4251404404640198},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42248696088790894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35606348514556885},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16679376363754272},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.11549657583236694},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C49204034","wikidata":"https://www.wikidata.org/wiki/Q52139","display_name":"Climatology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2619947201","https://openalex.org/W2742943414","https://openalex.org/W2798725893","https://openalex.org/W2895845501","https://openalex.org/W2904698318","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2950178297","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2962937869","https://openalex.org/W2962990649","https://openalex.org/W2963971014","https://openalex.org/W2964121744","https://openalex.org/W2964253311","https://openalex.org/W2965697393","https://openalex.org/W2981411942","https://openalex.org/W2981575209","https://openalex.org/W2981750519","https://openalex.org/W2984862483","https://openalex.org/W2986670728","https://openalex.org/W2988753485","https://openalex.org/W3009192917","https://openalex.org/W3009960797","https://openalex.org/W3034221024","https://openalex.org/W3034593503","https://openalex.org/W3035284526","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3041290354","https://openalex.org/W3093300941","https://openalex.org/W3101167253","https://openalex.org/W3112479442","https://openalex.org/W3115195697","https://openalex.org/W3116807031","https://openalex.org/W3171933509","https://openalex.org/W3176425931","https://openalex.org/W3180214828","https://openalex.org/W3193296307","https://openalex.org/W4205277845","https://openalex.org/W6761044565","https://openalex.org/W6765766786","https://openalex.org/W6774117908","https://openalex.org/W6780842026"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1,30,180],"is":[2,118,134,194,219],"a":[3,70,139],"challenging":[4],"task":[5],"that":[6,143],"captures":[7],"different":[8],"visual":[9,19,56],"parts":[10],"and":[11,20,50,171,203,233],"describes":[12],"them":[13],"in":[14,26,59,129,148,205],"sentences,":[15,67],"for":[16,181],"it":[17],"requires":[18],"linguistic":[21],"coherence.":[22],"The":[23,126,163,209],"attention":[24,95],"mechanism":[25,96],"the":[27,40,48,51,55,60,85,88,92,103,108,115,122,130,145,149,153,160,169,178,186,190,198,201,206,212,222],"current":[28,161],"video":[29,229],"method":[31],"learns":[32],"to":[33,36,97,158,176,235],"assign":[34],"weight":[35],"each":[37],"frame,":[38],"promoting":[39],"decoder":[41],"dynamically.":[42],"This":[43],"may":[44],"not":[45],"explicitly":[46],"model":[47],"correlation":[49],"temporal":[52,81],"coherence":[53],"of":[54,80,94,152,211,224],"features":[57],"extracted":[58],"sequence":[61,82,99],"frames.":[62],"To":[63],"generate":[64],"semantically":[65],"coherent":[66],"we":[68,137],"propose":[69],"new":[71],"Visual-aware":[72,214],"Attention":[73,215],"(VA)":[74],"model,":[75],"which":[76],"concatenates":[77],"dynamic":[78],"changes":[79],"frames":[83],"with":[84,185],"words":[86],"at":[87],"previous":[89,123,154],"moment,":[90],"as":[91,156],"input":[93,157],"extract":[98],"features.":[100],"In":[101],"addition,":[102],"prevalent":[104],"approaches":[105],"widely":[106],"use":[107],"Teacher-forcing":[109],"(TF)":[110],"learning":[111],"during":[112],"training,":[113],"where":[114],"next":[116],"token":[117,155],"generated":[119,132],"conditioned":[120],"on":[121,227],"ground-truth":[124],"tokens.":[125],"semantic":[127,146],"information":[128,147],"previously":[131],"tokens":[133],"lost.":[135],"Therefore,":[136],"design":[138],"Self-forcing":[140],"(SF)":[141],"stream":[142],"takes":[144],"probability":[150],"distribution":[151],"enhance":[159],"token.":[162],"Dual-stream":[164,187,216],"Decoder":[165,188,217],"(DD)":[166],"architecture":[167],"unifies":[168],"TF":[170,207],"SF":[172],"streams,":[173],"generating":[174],"sen-tences":[175],"promote":[177],"annotated":[179],"both":[182],"streams.":[183],"Meanwhile,":[184],"utilized,":[189],"ex-posure":[191],"bias":[192],"problem":[193],"alleviated,":[195],"caused":[196],"by":[197],"discrepancy":[199],"between":[200],"training":[202],"testing":[204],"learning.":[208],"effectiveness":[210],"proposed":[213],"(VADD)":[218],"demonstrated":[220],"through":[221],"result":[223],"ex-perimental":[225],"studies":[226],"Microsoft":[228],"description":[230],"(MSVD)":[231],"corpus":[232],"MSR-Video":[234],"text":[236],"(MSR-VTT)":[237],"datasets.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}