{"id":"https://openalex.org/W2981575209","doi":"https://doi.org/10.1145/3343031.3350932","title":"Attention-based Densely Connected LSTM for Video Captioning","display_name":"Attention-based Densely Connected LSTM for Video Captioning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981575209","doi":"https://doi.org/10.1145/3343031.3350932","mag":"2981575209"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5067696234","display_name":"Yongqing Zhu","orcid":"https://orcid.org/0000-0003-0092-5743"},"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":"Yongqing Zhu","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"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":"Shuqiang Jiang","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"802","last_page":"810"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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":0.9951000213623047,"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":0.9572155475616455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.858024001121521},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8277570605278015},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5790373682975769},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.53146892786026},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5162132382392883},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4925709366798401},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4844672679901123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47772499918937683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45233628153800964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3463713526725769},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3181399703025818},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14030611515045166}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9572155475616455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.858024001121521},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8277570605278015},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5790373682975769},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.53146892786026},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5162132382392883},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4925709366798401},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4844672679901123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47772499918937683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45233628153800964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3463713526725769},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3181399703025818},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14030611515045166},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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:10.1145/3343031.3350932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1591801644","https://openalex.org/W1601567445","https://openalex.org/W1686810756","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2425121537","https://openalex.org/W2535697732","https://openalex.org/W2556388456","https://openalex.org/W2584992898","https://openalex.org/W2593390416","https://openalex.org/W2596720518","https://openalex.org/W2621571501","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2792265253","https://openalex.org/W2807834696","https://openalex.org/W2808647806","https://openalex.org/W2890904455","https://openalex.org/W2904452845","https://openalex.org/W2913618459","https://openalex.org/W2950621961","https://openalex.org/W2962907269","https://openalex.org/W2963177403","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2963870701","https://openalex.org/W2963971014","https://openalex.org/W2964121744","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W2978329087","https://openalex.org/W3098682680","https://openalex.org/W3157598734"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W3119155061","https://openalex.org/W4287548803","https://openalex.org/W4288350158","https://openalex.org/W2946205552","https://openalex.org/W2905238334","https://openalex.org/W3024381485","https://openalex.org/W2953872833","https://openalex.org/W4295267149","https://openalex.org/W2566606998"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Networks":[2],"(RNNs),":[3],"especially":[4],"the":[5,22,30,35,45,49,60,69,76,82,89,134,139,142,160,183,191,208,215,221],"Long":[6,117],"Short-Term":[7,118],"Memory":[8,119],"(LSTM),":[9],"have":[10],"been":[11],"widely":[12],"used":[13,204],"for":[14],"video":[15,27,205],"captioning,":[16],"since":[17],"they":[18],"can":[19],"cope":[20],"with":[21,172],"temporal":[23,46],"dependencies":[24,47,97,193],"within":[25,48],"both":[26],"frames":[28],"and":[29,98,214,217],"corresponding":[31],"descriptions.":[32],"However,":[33],"as":[34],"sequence":[36],"gets":[37],"longer,":[38],"it":[39],"becomes":[40],"much":[41],"harder":[42],"to":[43,67,75,81,123,133,147,158,182],"handle":[44],"sequence.":[50],"And":[51],"in":[52,105],"traditional":[53],"LSTM,":[54],"previously":[55],"generated":[56,84,102],"hidden":[57,85,103,164],"states":[58],"except":[59],"last":[61,83],"one":[62],"do":[63],"not":[64],"work":[65],"directly":[66,99,145,170],"predict":[68],"current":[70,135,143],"word.":[71],"This":[72],"may":[73],"lead":[74],"predicted":[77],"word":[78],"highly":[79],"related":[80,146],"state":[86,144],"other":[87],"than":[88],"overall":[90],"context.":[91],"To":[92],"better":[93],"capture":[94],"long":[95],"range":[96],"leverage":[100],"early":[101],"states,":[104],"this":[106,189],"work,":[107],"we":[108],"propose":[109],"a":[110],"novel":[111],"model":[112,159],"named":[113],"Attention-based":[114],"Densely":[115],"Connected":[116],"(DenseLSTM).":[120],"In":[121,188],"DenseLSTM,":[122],"ensure":[124],"maximum":[125],"information":[126],"flow,":[127],"all":[128,148,173],"previous":[129,150],"cells":[130],"are":[131,194],"connected":[132,171],"cell,":[136],"which":[137],"makes":[138],"updating":[140],"of":[141,162,223],"its":[149,174],"states.":[151,165],"Furthermore,":[152],"an":[153],"attention":[154],"mechanism":[155],"is":[156,169],"designed":[157],"impacts":[161],"different":[163],"Because":[166],"each":[167,177],"cell":[168,178],"successive":[175],"cells,":[176],"has":[179],"direct":[180],"access":[181],"gradients":[184],"from":[185],"later":[186],"ones.":[187],"way,":[190],"long-range":[192],"more":[195],"effectively":[196],"captured.":[197],"We":[198],"perform":[199],"experiments":[200],"on":[201],"two":[202],"publicly":[203],"captioning":[206],"datasets:":[207],"Microsoft":[209],"Video":[210],"Description":[211],"Corpus":[212],"(MSVD)":[213],"MSR-VTT,":[216],"experimental":[218],"results":[219],"illustrate":[220],"effectiveness":[222],"DenseLSTM.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}