{"id":"https://openalex.org/W4384519194","doi":"https://doi.org/10.1109/tcsvt.2023.3296196","title":"TLDW: Extreme Multimodal Summarization of News Videos","display_name":"TLDW: Extreme Multimodal Summarization of News Videos","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384519194","doi":"https://doi.org/10.1109/tcsvt.2023.3296196"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3296196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3296196","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/A5055848990","display_name":"Peggy Tang","orcid":"https://orcid.org/0000-0003-3394-0114"},"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":"Peggy Tang","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668926","display_name":"Kun Hu","orcid":"https://orcid.org/0000-0002-6891-8059"},"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":"Kun Hu","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433824","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-6926-0538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["International Digital Economy Academy, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy, Shenzhen, Guangdong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443935","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"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":"Zhiyong Wang","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055848990"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.597,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85570754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"3","first_page":"1469","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7695490121841431},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7240960597991943},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4753689169883728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47083592414855957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46793410181999207},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43850576877593994},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4310153126716614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3648856282234192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695490121841431},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7240960597991943},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4753689169883728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47083592414855957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46793410181999207},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43850576877593994},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4310153126716614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3648856282234192},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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.2023.3296196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3296196","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/G39296982","display_name":null,"funder_award_id":"DP210102674","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":58,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1958932515","https://openalex.org/W1981276685","https://openalex.org/W2105482032","https://openalex.org/W2118210476","https://openalex.org/W2152433968","https://openalex.org/W2242099022","https://openalex.org/W2512435841","https://openalex.org/W2557264465","https://openalex.org/W2606974598","https://openalex.org/W2885377438","https://openalex.org/W2888482885","https://openalex.org/W2890721473","https://openalex.org/W2962785754","https://openalex.org/W2962907269","https://openalex.org/W2962972512","https://openalex.org/W2963351113","https://openalex.org/W2963508075","https://openalex.org/W2963971014","https://openalex.org/W2964167369","https://openalex.org/W2970419734","https://openalex.org/W2973131617","https://openalex.org/W2979826702","https://openalex.org/W2981642654","https://openalex.org/W2982084422","https://openalex.org/W2988753485","https://openalex.org/W2997326549","https://openalex.org/W3025262802","https://openalex.org/W3034383590","https://openalex.org/W3034991617","https://openalex.org/W3035050380","https://openalex.org/W3087792975","https://openalex.org/W3090080067","https://openalex.org/W3098682680","https://openalex.org/W3099396524","https://openalex.org/W3100439847","https://openalex.org/W3100932507","https://openalex.org/W3104404235","https://openalex.org/W3109862485","https://openalex.org/W3113146884","https://openalex.org/W3151369355","https://openalex.org/W3154224759","https://openalex.org/W3175888430","https://openalex.org/W3196673616","https://openalex.org/W3202059497","https://openalex.org/W3210314917","https://openalex.org/W4226189850","https://openalex.org/W4283363598","https://openalex.org/W4285413108","https://openalex.org/W4299783144","https://openalex.org/W6621906925","https://openalex.org/W6631501603","https://openalex.org/W6682631176","https://openalex.org/W6737479944","https://openalex.org/W6757817989","https://openalex.org/W6771915120","https://openalex.org/W6791353385","https://openalex.org/W6803537622"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W1517524280","https://openalex.org/W4323520239"],"abstract_inverted_index":{"Multimodal":[0,57,60],"summarisation":[1],"with":[2,59,86],"multimodal":[3,28,49,123,126],"output":[4],"is":[5,135],"drawing":[6],"increasing":[7],"attention":[8],"due":[9],"to":[10,23,38,74,78],"the":[11,40,45,64,98,105,143,149,152,155,164],"rapid":[12],"growth":[13],"of":[14,47,66,93,119,151,192],"multimedia":[15],"data.":[16],"While":[17],"several":[18],"methods":[19],"have":[20],"been":[21],"proposed":[22],"summarise":[24,79],"visual-text":[25],"contents,":[26],"their":[27],"outputs":[29],"are":[30],"not":[31],"succinct":[32],"enough":[33],"at":[34],"an":[35,87],"extreme":[36,48],"level":[37],"address":[39],"information":[41],"overload":[42],"issue.":[43],"To":[44,162],"end":[46],"summarisation,":[50],"we":[51,169],"introduce":[52],"a":[53,80,84,110,171],"new":[54],"task,":[55,168],"eXtreme":[56],"Summarisation":[58],"Output":[61],"(XMSMO)":[62],"for":[63],"scenario":[65],"TL;DW":[67],"-":[68],"Too":[69],"Long;":[70],"Didn\u2019t":[71],"Watch,":[72],"akin":[73],"TL;DR.":[75],"XMSMO":[76],"aims":[77],"video-document":[81,178],"pair":[82],"into":[83],"summary":[85,100],"extremely":[88],"short":[89],"length,":[90],"which":[91],"consists":[92],"one":[94,102],"cover":[95],"frame":[96],"as":[97,104],"visual":[99,144],"and":[101,129,145,194,199],"sentence":[103],"textual":[106,146],"summary.":[107],"We":[108],"propose":[109],"novel":[111],"unsupervised":[112],"Hierarchical":[113],"Optimal":[114],"Transport":[115],"Network":[116],"(HOT-Net)":[117],"consisting":[118],"three":[120],"components:":[121],"hierarchical":[122,125],"encoder,":[124],"fusion":[127],"decoder,":[128],"optimal":[130,159],"transport":[131,160],"solver.":[132],"Our":[133,197],"method":[134,186],"trained,":[136],"without":[137],"using":[138],"reference":[139],"summaries,":[140],"by":[141,175],"optimising":[142],"coverage":[147],"from":[148],"perspectives":[150],"distance":[153],"between":[154],"semantic":[156],"distributions":[157],"under":[158],"plans.":[161],"facilitate":[163],"study":[165],"on":[166],"this":[167],"constructed":[170],"large-scale":[172],"dataset,":[173],"XMSMO-News,":[174],"harvesting":[176],"4,891":[177],"pairs.":[179],"The":[180],"experimental":[181],"results":[182],"show":[183],"that":[184],"our":[185],"achieves":[187],"promising":[188],"performance":[189],"in":[190,206],"terms":[191],"ROUGE":[193],"IoU":[195],"metrics.":[196],"dataset":[198],"source":[200],"code":[201],"will":[202],"be":[203],"publicly":[204],"available":[205],"GitHub.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}
