{"id":"https://openalex.org/W3201981562","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534164","title":"Dense Video Captioning with Hierarchical Attention-Based Encoder-Decoder Networks","display_name":"Dense Video Captioning with Hierarchical Attention-Based Encoder-Decoder Networks","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201981562","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534164","mag":"3201981562"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5059166825","display_name":"Mingjing Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjing Yu","raw_affiliation_strings":["Guangdong Key Laboratory of Information Security Technology","Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","School of Computer Science and Engineering, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Information Security Technology","institution_ids":[]},{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034213282","display_name":"Huicheng Zheng","orcid":"https://orcid.org/0000-0002-6729-4176"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huicheng Zheng","raw_affiliation_strings":["Guangdong Key Laboratory of Information Security Technology","Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","School of Computer Science and Engineering, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Information Security Technology","institution_ids":[]},{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697562","display_name":"Zehua Liu","orcid":"https://orcid.org/0000-0003-3293-5356"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Liu","raw_affiliation_strings":["Guangdong Key Laboratory of Information Security Technology","Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","School of Computer Science and Engineering, Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Information Security Technology","institution_ids":[]},{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Machine Intelligence and Advanced Computing, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059166825"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.39908497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9944999814033508,"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":0.9632948637008667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8654400110244751},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6472083330154419},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5685538053512573},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5655811429023743},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49434471130371094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4918975830078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4910440444946289},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48957595229148865},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45349180698394775},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43404871225357056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15305498242378235}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9632948637008667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8654400110244751},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6472083330154419},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5685538053512573},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5655811429023743},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49434471130371094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4918975830078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4910440444946289},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48957595229148865},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45349180698394775},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43404871225357056},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15305498242378235},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G2111632626","display_name":null,"funder_award_id":"61976231,U1611461,61573387,61172141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1665214252","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2277195237","https://openalex.org/W2613718673","https://openalex.org/W2621571501","https://openalex.org/W2755876276","https://openalex.org/W2775755471","https://openalex.org/W2904291752","https://openalex.org/W2945223572","https://openalex.org/W2953461088","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2963084599","https://openalex.org/W2963315828","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2963576560","https://openalex.org/W2963613897","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2964015378","https://openalex.org/W2964049455","https://openalex.org/W2964241990","https://openalex.org/W2968104955","https://openalex.org/W2969844053","https://openalex.org/W3000240650","https://openalex.org/W3034815696","https://openalex.org/W3035160838","https://openalex.org/W3035392611","https://openalex.org/W3036900224","https://openalex.org/W3047922786","https://openalex.org/W4385245566","https://openalex.org/W6637242042","https://openalex.org/W6682983702","https://openalex.org/W6726873649","https://openalex.org/W6729046916","https://openalex.org/W6739901393","https://openalex.org/W6748524686","https://openalex.org/W6765766786","https://openalex.org/W6775036685"],"related_works":["https://openalex.org/W4210416330","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","https://openalex.org/W2993670781"],"abstract_inverted_index":{"Dense":[0],"video":[1,114,125],"captioning":[2],"is":[3,75],"a":[4,143,187,199],"challenging":[5],"task":[6],"with":[7,81],"the":[8,62,68,70,82,106,121,124,130,158,168,183,193,217],"goal":[9],"of":[10,36,65,72,84],"localizing":[11],"and":[12,25,42,101,126,128,134,162,198],"describing":[13],"all":[14],"events":[15],"in":[16,50,67,123],"an":[17,152,163],"untrimmed":[18],"video,":[19,69],"taking":[20],"into":[21,182],"account":[22],"both":[23],"visual":[24,133,150],"text":[26,127,135,196],"information.":[27,58,207],"Although":[28],"existing":[29],"methods":[30],"have":[31],"made":[32,49],"some":[33],"achievements,":[34],"most":[35,131,159,194],"them":[37],"suffer":[38],"from":[39],"missing":[40],"details":[41],"inferior":[43],"captioning.":[44,115],"Recent":[45],"progress":[46],"has":[47,175],"been":[48,176],"using":[51],"object":[52,153],"features":[53,136,181,197],"to":[54,61,191,203],"supplement":[55],"more":[56],"detailed":[57],"However,":[59],"due":[60],"considerable":[63],"number":[64],"objects":[66,74,161],"representation":[71],"learning":[73,148],"often":[76],"noisy,":[77],"which":[78],"may":[79],"interfere":[80],"generation":[83],"correct":[85],"captions.":[86],"We":[87],"also":[88],"notice":[89],"that":[90],"realworld":[91],"video-text":[92,108],"data":[93],"involve":[94],"different":[95],"granularity":[96],"levels,":[97],"such":[98],"as":[99],"objects/words":[100],"events/sentences.":[102],"Therefore,":[103],"we":[104,141],"propose":[105],"hierarchical":[107,144,210],"attention-based":[109],"encoder-decoder":[110],"networks":[111],"for":[112,147,178],"dense":[113],"The":[116,208],"proposed":[117,209],"method":[118],"successfully":[119],"considers":[120],"hierarchy":[122],"exploits":[129],"relevant":[132,160],"when":[137],"generating":[138],"caption.":[139],"Specially,":[140],"design":[142],"attention":[145,154,165,189,201,211],"encoder":[146],"complex":[149],"information:":[151],"module":[155,166,190,202],"focusing":[156],"on":[157,216],"event":[164],"modeling":[167],"long-range":[169],"temporal":[170],"context.":[171],"A":[172],"corresponding":[173],"decoder":[174],"built":[177],"translating":[179],"multi-level":[180],"linguistic":[184],"description,":[185],"i.e.,":[186],"word":[188],"exploit":[192],"correlated":[195],"sentence":[200],"leverage":[204],"high-level":[205],"semantic":[206],"mechanism":[212],"achieves":[213],"state-of-the-art":[214],"performance":[215],"ActivityNet":[218],"Captions":[219],"dataset.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}