{"id":"https://openalex.org/W2969844053","doi":"https://doi.org/10.1109/tcsvt.2019.2936526","title":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","display_name":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","publication_year":2019,"publication_date":"2019-08-22","ids":{"openalex":"https://openalex.org/W2969844053","doi":"https://doi.org/10.1109/tcsvt.2019.2936526","mag":"2969844053"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2019.2936526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2936526","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/A5081565915","display_name":"Zhiwang Zhang","orcid":"https://orcid.org/0000-0002-8867-3888"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhiwang Zhang","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082181536","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0003-2775-9730"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103121138","display_name":"Chuanqi Tan","orcid":"https://orcid.org/0000-0003-1197-4807"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanqi Tan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081565915"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.822,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.88673429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":"9","first_page":"3130","last_page":"3139"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9642869234085083},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8772213459014893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8590823411941528},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7423523664474487},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7413005232810974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5902125835418701},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5897952914237976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5819122791290283},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.578832745552063},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46086323261260986},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4131256639957428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3913816511631012},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17420682311058044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08489900827407837}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9642869234085083},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8772213459014893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590823411941528},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7423523664474487},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7413005232810974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5902125835418701},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5897952914237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819122791290283},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.578832745552063},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46086323261260986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4131256639957428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3913816511631012},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17420682311058044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08489900827407837},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2019.2936526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2936526","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":[],"awards":[{"id":"https://openalex.org/G4280650047","display_name":null,"funder_award_id":"FT180100116","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1895577753","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2080672747","https://openalex.org/W2110693578","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2302086703","https://openalex.org/W2471143248","https://openalex.org/W2519328139","https://openalex.org/W2526544345","https://openalex.org/W2535977253","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2607119937","https://openalex.org/W2755876276","https://openalex.org/W2798725893","https://openalex.org/W2947454602","https://openalex.org/W2950568498","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963495494","https://openalex.org/W2963576560","https://openalex.org/W2963656855","https://openalex.org/W2963753226","https://openalex.org/W2963843052","https://openalex.org/W2963916161","https://openalex.org/W2963954913","https://openalex.org/W2963971014","https://openalex.org/W2964049455","https://openalex.org/W2964241990","https://openalex.org/W2964253311","https://openalex.org/W6628927728","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6729046916","https://openalex.org/W6730028046","https://openalex.org/W6898505805"],"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/W4289422896"],"abstract_inverted_index":{"In":[0],"this":[1,58,165,206],"work,":[2],"we":[3,35,74],"propose":[4,90],"a":[5,29,82,91,103],"division-and-summarization":[6],"(DaS)":[7],"framework":[8,225],"for":[9,57,205,226],"dense":[10,77,227],"video":[11,18,33,78,186,228],"captioning.":[12,229],"After":[13],"partitioning":[14],"each":[15,24,43],"untrimmed":[16],"long":[17],"as":[19,81,113,147,152,192,197],"multiple":[20],"event":[21,25,72,145,166,190,207],"proposals,":[22],"where":[23],"proposal":[26,146,191],"consists":[27],"of":[28,31,120,220],"set":[30],"short":[32],"segments,":[34],"extract":[36],"visual":[37,83,121,138,161,182],"feature":[38],"(e.g.,":[39],"C3D":[40],"feature)":[41],"from":[42,132,140,175,184],"segment":[44],"and":[45,89,136,150,160,180,195],"use":[46],"the":[47,62,70,76,118,124,133,137,148,153,173,176,181,193,198,213,218],"existing":[48],"image/video":[49],"captioning":[50,79],"approach":[51,100],"to":[52,108,155,164,200],"generate":[53,201],"one":[54,114,144,189,202],"sentence":[55,86,116,204],"description":[56],"segment.":[59],"Considering":[60],"that":[61],"generated":[63,111,134],"sentences":[64,112,135],"contain":[65],"rich":[66],"semantic":[67,130,159],"descriptions":[68],"about":[69],"whole":[71],"proposal,":[73],"formulate":[75],"task":[80],"cue":[84],"aided":[85],"summarization":[87],"problem":[88],"new":[92,104],"two":[93],"stage":[94],"Long":[95],"Short":[96],"Term":[97],"Memory":[98],"(LSTM)":[99],"equipped":[101],"with":[102,117],"hierarchical":[105],"attention":[106],"mechanism":[107],"summarize":[109,157],"all":[110,129,141,185],"descriptive":[115,203],"aid":[119],"features.":[122],"Specifically,":[123],"first-stage":[125,177],"LSTM":[126,170,178],"network":[127,171,179],"takes":[128,172],"words":[131],"features":[139,183],"segments":[142,187],"within":[143,188],"input,":[149,194],"acts":[151,196],"encoder":[154],"effectively":[156],"both":[158],"information":[162],"related":[163],"proposal.":[167,208],"The":[168],"second-stage":[169],"output":[174],"decoder":[199],"Our":[209],"comprehensive":[210],"experiments":[211],"on":[212],"ActivityNet":[214],"Captions":[215],"dataset":[216],"demonstrate":[217],"effectiveness":[219],"our":[221],"newly":[222],"proposed":[223],"DaS":[224]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
