{"id":"https://openalex.org/W3090267019","doi":"https://doi.org/10.1109/icip40778.2020.9190636","title":"Hierarchical Model For Long-Length Video Summarization With Adversarially Enhanced Audio/Visual Features","display_name":"Hierarchical Model For Long-Length Video Summarization With Adversarially Enhanced Audio/Visual Features","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3090267019","doi":"https://doi.org/10.1109/icip40778.2020.9190636","mag":"3090267019"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/A5100776033","display_name":"Hansol Lee","orcid":"https://orcid.org/0000-0002-6912-7128"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hansol Lee","raw_affiliation_strings":["Seoul National University of Science and Technology, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071978775","display_name":"Gyemin Lee","orcid":"https://orcid.org/0000-0001-6785-8739"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyemin Lee","raw_affiliation_strings":["Seoul National University of Science and Technology, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100776033"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":null,"apc_paid":null,"fwci":0.3925,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62558024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"723","last_page":"727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9934999942779541,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9429948329925537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781041145324707},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.694139301776886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42998185753822327},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4282371401786804},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3497040271759033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34827035665512085},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26704177260398865}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9429948329925537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781041145324707},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.694139301776886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42998185753822327},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4282371401786804},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3497040271759033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34827035665512085},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26704177260398865}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1923404803","https://openalex.org/W2099471712","https://openalex.org/W2115857089","https://openalex.org/W2148154194","https://openalex.org/W2194775991","https://openalex.org/W2737677090","https://openalex.org/W2781922022","https://openalex.org/W2883047779","https://openalex.org/W2895758197","https://openalex.org/W2963026017","https://openalex.org/W2963322247","https://openalex.org/W2963545239","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W4320013936","https://openalex.org/W6640257725","https://openalex.org/W6677302653","https://openalex.org/W6713349023","https://openalex.org/W6747656205"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W4306886878"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,68,111],"propose":[4],"a":[5,70,114],"novel":[6],"supervised":[7],"method":[8,145],"for":[9,43,61,149],"summarizing":[10],"long-length":[11,45],"videos.":[12,152],"Many":[13],"recent":[14],"approaches":[15,51],"presented":[16],"promising":[17],"results":[18],"in":[19,24,30,132],"video":[20,128],"summarization.":[21],"However,":[22],"videos":[23,46],"most":[25,50],"benchmark":[26],"datasets":[27],"are":[28],"short":[29],"duration":[31],"(<;":[32],"10":[33],"minutes),":[34],"and":[35,76,93],"the":[36,62,83,91,101,135,140],"methods":[37],"often":[38],"do":[39],"not":[40],"work":[41],"well":[42],"very":[44,150],"(>1":[47],"hour).":[48],"Furthermore,":[49],"only":[52],"use":[53],"visual":[54,77],"features,":[55],"while":[56],"audios":[57],"provide":[58],"useful":[59],"information":[60],"task.":[63],"Based":[64],"on":[65,139],"these":[66],"observations,":[67],"present":[69],"model":[71,88,98],"that":[72,129,143],"exploits":[73],"both":[74,90],"audio":[75],"features.":[78],"To":[79,107],"handle":[80],"long":[81,151],"videos,":[82,122],"hierarchical":[84],"structure":[85],"of":[86,117,134],"our":[87,109,144],"captures":[89],"short-term":[92],"long-term":[94],"temporal":[95],"dependencies.":[96],"Our":[97],"also":[99],"refines":[100],"extracted":[102],"features":[103],"using":[104],"adversarial":[105],"networks.":[106],"demonstrate":[108],"model,":[110],"have":[112],"collected":[113],"new":[115],"dataset":[116,141],"28":[118],"baseball":[119],"(~3.5":[120],"hours)":[121],"accompanied":[123],"by":[124],"an":[125],"editorial":[126],"summary":[127],"is":[130],"5%":[131],"length":[133],"original":[136],"video.":[137],"Evaluation":[138],"suggests":[142],"produces":[146],"quality":[147],"summaries":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2025-10-10T00:00:00"}
