{"id":"https://openalex.org/W2964137974","doi":"https://doi.org/10.1145/2964284.2967258","title":"Bidirectional Long-Short Term Memory for Video Description","display_name":"Bidirectional Long-Short Term Memory for Video Description","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2964137974","doi":"https://doi.org/10.1145/2964284.2967258","mag":"2964137974"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["The University of Queensland & University of Electronic Science and Technology of China, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland & University of Electronic Science and Technology of China, Brisbane, Australia","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"440"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9630550742149353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8989556431770325},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6015691161155701},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5800704956054688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664349794387817},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5580849647521973},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5375691652297974},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5183999538421631},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.47364556789398193},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4648859202861786},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4531146287918091},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41755232214927673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3471992015838623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.338601678609848},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26991868019104004},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23550257086753845}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9630550742149353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8989556431770325},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6015691161155701},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5800704956054688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664349794387817},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5580849647521973},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5375691652297974},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5183999538421631},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47364556789398193},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4648859202861786},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4531146287918091},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41755232214927673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3471992015838623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.338601678609848},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26991868019104004},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23550257086753845},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2967258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"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":35,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1897761818","https://openalex.org/W1900913856","https://openalex.org/W1905882502","https://openalex.org/W1910300841","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1975864240","https://openalex.org/W2014021126","https://openalex.org/W2041259983","https://openalex.org/W2051398366","https://openalex.org/W2057378058","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2080672747","https://openalex.org/W2087341100","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2150355110","https://openalex.org/W2154652894","https://openalex.org/W2155893237","https://openalex.org/W2164290393","https://openalex.org/W2167905777","https://openalex.org/W2197084977","https://openalex.org/W2618530766","https://openalex.org/W2963576560","https://openalex.org/W2964241990"],"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/W2805949325","https://openalex.org/W4300536205"],"abstract_inverted_index":{"Video":[0,146],"captioning":[1,37,138],"has":[2],"been":[3],"attracting":[4],"broad":[5],"research":[6],"attention":[7],"in":[8,53,104],"multimedia":[9],"community.":[10],"However,":[11],"most":[12],"existing":[13],"approaches":[14],"either":[15],"ignore":[16],"temporal":[17,27,51],"information":[18],"among":[19],"video":[20,36,66,92,137],"frames":[21],"or":[22],"just":[23],"employ":[24],"local":[25],"contextual":[26],"knowledge.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,56,88],"propose":[33],"a":[34,59,70,74,141],"novel":[35],"framework,":[38],"termed":[39],"as":[40,162],"\\emph{Bidirectional":[41],"Long-Short":[42],"Term":[43],"Memory}":[44],"(BiLSTM),":[45],"which":[46],"deeply":[47],"captures":[48],"bidirectional":[49],"global":[50],"structure":[52],"video.":[54],"Specifically,":[55],"first":[57],"devise":[58],"joint":[60],"visual":[61,80,112,119],"modelling":[62],"approach":[63,161],"to":[64,164],"encode":[65],"data":[67],"by":[68],"combining":[69],"forward":[71],"LSTM":[72,76],"pass,":[73,77],"backward":[75],"together":[78],"with":[79],"features":[81,120],"from":[82],"Convolutional":[83],"Neural":[84],"Networks":[85],"(CNNs).":[86],"Then,":[87],"inject":[89],"the":[90,95,132,151,156,159],"derived":[91],"representation":[93],"into":[94],"subsequent":[96],"language":[97],"model":[98],"for":[99,125],"initialization.":[100],"The":[101],"benefits":[102],"are":[103],"two":[105],"folds:":[106],"1)":[107],"comprehensively":[108],"preserving":[109],"sequential":[110],"and":[111,114,121,127,150],"information;":[113],"2)":[115],"adaptively":[116],"learning":[117],"dense":[118],"sparse":[122],"semantic":[123],"representations":[124],"videos":[126],"sentences,":[128],"respectively.":[129],"We":[130],"verify":[131],"effectiveness":[133],"of":[134,158],"our":[135],"proposed":[136,160],"framework":[139],"on":[140],"commonly-used":[142],"benchmark,":[143],"i.e.,":[144],"Microsoft":[145],"Description":[147],"(MSVD)":[148],"corpus,":[149],"experimental":[152],"results":[153],"demonstrate":[154],"that":[155],"superiority":[157],"compared":[163],"several":[165],"state-of-the-art":[166],"methods.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}