{"id":"https://openalex.org/W4372349802","doi":"https://doi.org/10.1109/icassp49357.2023.10096265","title":"MHSCNET: A Multimodal Hierarchical Shot-Aware Convolutional Network for Video Summarization","display_name":"MHSCNET: A Multimodal Hierarchical Shot-Aware Convolutional Network for Video Summarization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349802","doi":"https://doi.org/10.1109/icassp49357.2023.10096265"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5081309714","display_name":"Wujiang Xu","orcid":"https://orcid.org/0000-0002-3500-1068"},"institutions":[{"id":"https://openalex.org/I4210132615","display_name":"Zhejiang Energy Group (China)","ror":"https://ror.org/03a2tkf74","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wujiang Xu","raw_affiliation_strings":["Ant Group,MYbank,Hangzhou,China","MYbank, Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,MYbank,Hangzhou,China","institution_ids":["https://openalex.org/I4210132615"]},{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069477050","display_name":"Runzhong Wang","orcid":"https://orcid.org/0000-0002-9566-738X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runzhong Wang","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750075","display_name":"Xiaobo Guo","orcid":"https://orcid.org/0000-0002-6817-626X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032783414","display_name":"Shaoshuai Li","orcid":"https://orcid.org/0000-0003-2949-668X"},"institutions":[{"id":"https://openalex.org/I4210132615","display_name":"Zhejiang Energy Group (China)","ror":"https://ror.org/03a2tkf74","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoshuai Li","raw_affiliation_strings":["Ant Group,MYbank,Hangzhou,China","MYbank, Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,MYbank,Hangzhou,China","institution_ids":["https://openalex.org/I4210132615"]},{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013270229","display_name":"Qiongxu Ma","orcid":"https://orcid.org/0000-0003-2465-4941"},"institutions":[{"id":"https://openalex.org/I4210132615","display_name":"Zhejiang Energy Group (China)","ror":"https://ror.org/03a2tkf74","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiongxu Ma","raw_affiliation_strings":["Ant Group,MYbank,Hangzhou,China","MYbank, Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,MYbank,Hangzhou,China","institution_ids":["https://openalex.org/I4210132615"]},{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101663677","display_name":"Yunan Zhao","orcid":"https://orcid.org/0000-0001-7725-906X"},"institutions":[{"id":"https://openalex.org/I4210132615","display_name":"Zhejiang Energy Group (China)","ror":"https://ror.org/03a2tkf74","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunan Zhao","raw_affiliation_strings":["Ant Group,MYbank,Hangzhou,China","MYbank, Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,MYbank,Hangzhou,China","institution_ids":["https://openalex.org/I4210132615"]},{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687098","display_name":"Sheng Guo","orcid":"https://orcid.org/0000-0003-1385-3152"},"institutions":[{"id":"https://openalex.org/I4210132615","display_name":"Zhejiang Energy Group (China)","ror":"https://ror.org/03a2tkf74","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Guo","raw_affiliation_strings":["Ant Group,MYbank,Hangzhou,China","MYbank, Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,MYbank,Hangzhou,China","institution_ids":["https://openalex.org/I4210132615"]},{"raw_affiliation_string":"MYbank, Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867605","display_name":"Zhenfeng Zhu","orcid":"https://orcid.org/0000-0001-7315-3276"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenfeng Zhu","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9822999835014343,"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":0.926980197429657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.870630145072937},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6519211530685425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6432010531425476},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5995680093765259},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5895407199859619},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5433678030967712},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4484618902206421},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34935063123703003},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3221256136894226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3207172155380249}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.926980197429657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870630145072937},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6519211530685425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6432010531425476},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5995680093765259},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5895407199859619},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5433678030967712},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4484618902206421},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34935063123703003},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3221256136894226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3207172155380249},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.41999998688697815,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W2097117768","https://openalex.org/W2526050071","https://openalex.org/W2529272619","https://openalex.org/W2737677090","https://openalex.org/W2788303226","https://openalex.org/W2902616437","https://openalex.org/W2949550202","https://openalex.org/W2963220254","https://openalex.org/W2963351448","https://openalex.org/W2963840672","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W2967038491","https://openalex.org/W2971202647","https://openalex.org/W3090254005","https://openalex.org/W3107252718","https://openalex.org/W3108154605","https://openalex.org/W3161098244","https://openalex.org/W3161349773","https://openalex.org/W3166396011","https://openalex.org/W4206423448","https://openalex.org/W4287107550","https://openalex.org/W4287777632","https://openalex.org/W6640109428","https://openalex.org/W6696085341","https://openalex.org/W6741802007","https://openalex.org/W6753059133","https://openalex.org/W6756070665","https://openalex.org/W6777481484","https://openalex.org/W6791353385","https://openalex.org/W6795976578","https://openalex.org/W6797265648"],"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/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4323520239"],"abstract_inverted_index":{"Video":[0],"summarization":[1,22,57,182],"is":[2],"an":[3],"essential":[4],"problem":[5,31],"in":[6,79,102,167],"signal":[7],"processing,":[8],"which":[9],"intends":[10],"to":[11,87,120,139],"produce":[12],"a":[13,28,89,103,111,135],"concise":[14],"summary":[15],"of":[16,58,70,173],"the":[17,25,35,40,55,59,64,98,122,127,141,148,156,163,168,174],"original":[18],"video.":[19,175],"Existing":[20],"video":[21,181],"approaches":[23],"regard":[24],"task":[26],"as":[27,118],"keyframe":[29,52],"selection":[30],"and":[32,66,92,96,105,150,170],"generally":[33],"construct":[34,88],"frame-wise":[36,94,123],"representation":[37,95,124,145],"by":[38,62,146],"combining":[39,126],"long-range":[41,151],"temporal":[42,152],"dependency":[43],"with":[44],"either":[45],"unimodal":[46],"or":[47],"bimodal":[48],"information.":[49,131],"The":[50],"optimal":[51],"should":[53],"offer":[54],"semantic":[56],"whole":[60],"content":[61],"exploiting":[63],"multimodal":[65,112,130],"shot-level":[67],"hierarchical":[68,113,136],"natures":[69,74],"videos,":[71],"however,":[72],"such":[73],"are":[75],"not":[76],"fully":[77],"exploited":[78],"existing":[80],"methods.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,109],"propose":[86,110],"more":[90],"powerful":[91],"robust":[93],"predict":[97,162],"frame-level":[99,144,164],"importance":[100,165],"score":[101,166],"fair":[104],"comprehensive":[106,128],"manner.":[107],"Specifically,":[108],"shot-aware":[114,143,158],"convolutional":[115],"network,":[116],"denoted":[117],"MHSCNet,":[119],"enhance":[121],"via":[125],"available":[129],"We":[132],"further":[133],"design":[134],"ShotConv":[137],"network":[138],"incorporate":[140],"adaptive":[142],"considering":[147],"short-range":[149],"dependencies.":[153],"Based":[154],"on":[155,178],"learned":[157],"representations,":[159],"MHSCNet":[160],"can":[161],"local":[169],"global":[171],"view":[172],"Extensive":[176],"experiments":[177],"two":[179],"standard":[180],"datasets":[183],"demonstrate":[184],"that":[185],"our":[186],"proposed":[187],"method":[188],"consistently":[189],"outperforms":[190],"state-of-the-arts.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
