{"id":"https://openalex.org/W2889418103","doi":"https://doi.org/10.1109/tcsvt.2018.2867286","title":"Dual-Stream Recurrent Neural Network for Video Captioning","display_name":"Dual-Stream Recurrent Neural Network for Video Captioning","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889418103","doi":"https://doi.org/10.1109/tcsvt.2018.2867286","mag":"2889418103"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2018.2867286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2018.2867286","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/A5054900679","display_name":"Ning Xu","orcid":"https://orcid.org/0000-0002-7526-4356"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006712","display_name":"Yongkang Wong","orcid":"https://orcid.org/0000-0002-1239-4428"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yongkang Wong","raw_affiliation_strings":["Smart Systems Institute, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Smart Systems Institute, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001185571","display_name":"Weizhi Nie","orcid":"https://orcid.org/0000-0002-0578-8138"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhi Nie","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033713097","display_name":"Yuting Su","orcid":"https://orcid.org/0000-0001-5165-204X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan Kankanhalli","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5054900679"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":6.7016,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.9759556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"29","issue":"8","first_page":"2482","last_page":"2493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9977999925613403,"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":0.8613145351409912},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8365356922149658},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7608792781829834},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6554176211357117},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6038905382156372},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.573282778263092},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5623072385787964},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5364025235176086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5360512733459473},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5093611478805542},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4670411944389343},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46469682455062866},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4421226978302002},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34673547744750977},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.26489731669425964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11526456475257874},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10754215717315674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613145351409912},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8365356922149658},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7608792781829834},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6554176211357117},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6038905382156372},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.573282778263092},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5623072385787964},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5364025235176086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360512733459473},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5093611478805542},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4670411944389343},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46469682455062866},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4421226978302002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34673547744750977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26489731669425964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11526456475257874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10754215717315674},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2018.2867286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2018.2867286","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":[{"id":"https://metadata.un.org/sdg/17","score":0.4699999988079071,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G2050428177","display_name":null,"funder_award_id":"61772359","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2660664952","display_name":null,"funder_award_id":"61472275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4750268492","display_name":null,"funder_award_id":"61502337","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6023223561","display_name":null,"funder_award_id":"2017YFC0820600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8290336390","display_name":null,"funder_award_id":"61525206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1861492603","https://openalex.org/W1893116441","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2153635508","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2251353663","https://openalex.org/W2316539885","https://openalex.org/W2318631040","https://openalex.org/W2320044133","https://openalex.org/W2322020277","https://openalex.org/W2339830253","https://openalex.org/W2342503568","https://openalex.org/W2343553806","https://openalex.org/W2384495648","https://openalex.org/W2425121537","https://openalex.org/W2504559372","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2530258459","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2560252981","https://openalex.org/W2584992898","https://openalex.org/W2604729005","https://openalex.org/W2607119937","https://openalex.org/W2613964630","https://openalex.org/W2737030113","https://openalex.org/W2739107216","https://openalex.org/W2807718466","https://openalex.org/W2963149042","https://openalex.org/W2963576560","https://openalex.org/W2963811219","https://openalex.org/W2963843052","https://openalex.org/W2964018924","https://openalex.org/W2964199361","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W3098682680","https://openalex.org/W3174290789","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6683167905","https://openalex.org/W6684090549","https://openalex.org/W6685670348","https://openalex.org/W6691419566","https://openalex.org/W6736419893","https://openalex.org/W6898505805"],"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":{"Recent":[0],"progress":[1],"in":[2],"using":[3],"recurrent":[4],"neural":[5],"networks":[6],"(RNNs)":[7],"for":[8,26,43,104,114,162],"video":[9,105],"description":[10],"has":[11],"attracted":[12],"an":[13,109,129],"increasing":[14],"interest,":[15],"due":[16],"to":[17,20,90,117,134,150],"its":[18],"capability":[19],"encode":[21],"a":[22,85,145],"sequence":[23],"of":[24,50,98,123,193],"frames":[25],"caption":[27,106,163],"generation.":[28,107,164],"While":[29],"existing":[30],"methods":[31],"have":[32,56],"studied":[33],"various":[34,191],"features":[35],"(e.g.,":[36,70],"CNN,":[37,39],"3D":[38],"and":[40,48,72,93,101,174],"semantic":[41,102],"attributes)":[42],"visual":[44,100],"encoding,":[45],"the":[46,95,120,136,152,183,194],"representation":[47],"fusion":[49,69],"heterogeneous":[51],"information":[52],"from":[53,159],"multi-modal":[54,68],"spaces":[55],"not":[57],"fully":[58],"explored.":[59],"Consider":[60],"that":[61,177],"different":[62],"modalities":[63],"are":[64],"often":[65],"asynchronous,":[66],"frame-level":[67],"concatenation":[71],"linear":[73],"fusion)":[74],"will":[75],"negatively":[76],"influence":[77],"each":[78,115],"modality.":[79,125],"In":[80],"this":[81],"paper,":[82],"we":[83,127],"propose":[84],"dual-stream":[86,146],"RNN":[87,111],"(DS-RNN)":[88],"framework":[89],"jointly":[91],"discover":[92],"integrate":[94,151],"hidden":[96,121,157],"states":[97,122,158],"both":[99,160],"streams":[103,161],"First,":[108],"encoding":[110],"is":[112,148],"used":[113],"stream":[116],"flexibly":[118],"exploit":[119],"respective":[124],"Specifically,":[126],"proposed":[128,195],"attentive":[130],"multi-grained":[131],"encoder":[132],"module":[133],"enhance":[135],"local":[137],"feature":[138],"learning":[139],"with":[140],"global":[141],"semantics":[142],"feature.":[143],"Then,":[144],"decoder":[147],"deployed":[149],"asynchronous":[153],"yet":[154],"complementary":[155],"sequential":[156],"Extensive":[165],"experiments":[166],"on":[167,190],"three":[168],"benchmark":[169],"datasets,":[170],"namely,":[171],"MSVD,":[172],"MSR-VTT,":[173],"MPII-MD,":[175],"show":[176],"DS-RNN":[178],"achieves":[179],"competitive":[180],"performance":[181],"against":[182],"state-of-the-art.":[184],"Additional":[185],"ablation":[186],"studies":[187],"were":[188],"conducted":[189],"variants":[192],"DS-RNN.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}