{"id":"https://openalex.org/W4409098760","doi":"https://doi.org/10.1109/tcsvt.2025.3557254","title":"Hybrid Siamese Masked Autoencoders as Unsupervised Video Summarizer","display_name":"Hybrid Siamese Masked Autoencoders as Unsupervised Video Summarizer","publication_year":2025,"publication_date":"2025-04-02","ids":{"openalex":"https://openalex.org/W4409098760","doi":"https://doi.org/10.1109/tcsvt.2025.3557254"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3557254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557254","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/A5100781348","display_name":"Yifei Xu","orcid":"https://orcid.org/0000-0003-3111-2518"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifei Xu","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038412759","display_name":"Zaiqiang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaiqiang Wu","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361375","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-3373-2999"},"institutions":[{"id":"https://openalex.org/I4210095980","display_name":"Zhejiang Runtu (China)","ror":"https://ror.org/00nf44j26","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095980"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Alltuu Inc., Hangzhou, Zhejiang, China","Alltuu Inc, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Alltuu Inc., Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210095980"]},{"raw_affiliation_string":"Alltuu Inc, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210095980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051678554","display_name":"Siqi Li","orcid":"https://orcid.org/0000-0003-4829-5680"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Li","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425944","display_name":"Wenlong Li","orcid":"https://orcid.org/0000-0002-5351-7076"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Li","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062629438","display_name":"Mingqi Li","orcid":"https://orcid.org/0000-0003-2412-9477"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqi Li","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079536457","display_name":"Yuan Rao","orcid":"https://orcid.org/0000-0003-1111-9210"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Rao","raw_affiliation_strings":["School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software, Xi’an Jiao-tong University,. Y. Xu is the corresponding author, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055284175","display_name":"Shuiguang Deng","orcid":"https://orcid.org/0000-0001-5015-6095"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuiguang Deng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","College of Computer Science and Technology in Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology in Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100781348"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06519849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"9","first_page":"9487","last_page":"9501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9789999723434448,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9789999723434448,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9549000263214111,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9251999855041504,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7185450196266174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6645979285240173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4766462743282318},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4678198993206024},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.4388897120952606},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41785526275634766},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2679329216480255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185450196266174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645979285240173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4766462743282318},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4678198993206024},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4388897120952606},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41785526275634766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2679329216480255}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3557254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557254","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/G1033609293","display_name":null,"funder_award_id":"CX(24)3132","funder_id":"https://openalex.org/F4320309870","funder_display_name":"Jiangsu Agricultural Science and Technology Innovation Fund"},{"id":"https://openalex.org/G3933354149","display_name":null,"funder_award_id":"2024JC-YBMS-498","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320309870","display_name":"Jiangsu Agricultural Science and Technology Innovation Fund","ror":"https://ror.org/0335n2618"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W1987366351","https://openalex.org/W2139009685","https://openalex.org/W2521028896","https://openalex.org/W2529272619","https://openalex.org/W2737677090","https://openalex.org/W2766630207","https://openalex.org/W2776277180","https://openalex.org/W2781922022","https://openalex.org/W2895907803","https://openalex.org/W2897091983","https://openalex.org/W2908469318","https://openalex.org/W2963026017","https://openalex.org/W2964158702","https://openalex.org/W2964167369","https://openalex.org/W2967219836","https://openalex.org/W2982084422","https://openalex.org/W2982672255","https://openalex.org/W2999428529","https://openalex.org/W3087792975","https://openalex.org/W3090254005","https://openalex.org/W3099156605","https://openalex.org/W3107128832","https://openalex.org/W3107252718","https://openalex.org/W3107283985","https://openalex.org/W3108154605","https://openalex.org/W3121043223","https://openalex.org/W3150815828","https://openalex.org/W3171941639","https://openalex.org/W3174989968","https://openalex.org/W3184549588","https://openalex.org/W3197449311","https://openalex.org/W3199848064","https://openalex.org/W3201625964","https://openalex.org/W3210314917","https://openalex.org/W4206423448","https://openalex.org/W4210333049","https://openalex.org/W4224920450","https://openalex.org/W4225769600","https://openalex.org/W4225925355","https://openalex.org/W4226103007","https://openalex.org/W4283069582","https://openalex.org/W4283363598","https://openalex.org/W4288456125","https://openalex.org/W4304080456","https://openalex.org/W4304080900","https://openalex.org/W4306955484","https://openalex.org/W4312748990","https://openalex.org/W4313156423","https://openalex.org/W4319300174","https://openalex.org/W4319300227","https://openalex.org/W4320015929","https://openalex.org/W4361249544","https://openalex.org/W4376607835","https://openalex.org/W4385815568","https://openalex.org/W4386453740","https://openalex.org/W4389161308","https://openalex.org/W4392904279","https://openalex.org/W4392904682","https://openalex.org/W4399418473","https://openalex.org/W4402702960","https://openalex.org/W4402703003","https://openalex.org/W4402980697"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"summarization":[1],"aims":[2],"to":[3,52,98,129,133,167],"seek":[4],"the":[5,41,100,119,135,143,150],"most":[6],"important":[7],"information":[8],"from":[9,76,103],"a":[10,56,65,77,126,169],"source":[11,202],"video":[12,23,68,170],"while":[13],"still":[14],"retaining":[15],"its":[16],"primary":[17],"content.":[18],"In":[19],"practical":[20],"application,":[21],"unsupervised":[22,67,187],"summarizers":[24],"are":[25,38,160],"acknowledged":[26],"for":[27,40],"their":[28],"flexibility":[29],"and":[30,91,107,176,188,191],"superiority":[31],"without":[32],"requiring":[33],"annotated":[34],"data.":[35],"However,":[36],"they":[37],"looking":[39],"determined":[42],"rules":[43],"on":[44,173],"how":[45],"much":[46],"each":[47],"frame":[48,105],"is":[49,206],"essential":[50],"enough":[51],"be":[53],"selected":[54,154],"as":[55],"summary.":[57,171],"Unlike":[58],"conventional":[59],"frame-based":[60],"scoring":[61],"methods,":[62,190],"we":[63],"propose":[64],"shot-level":[66],"summarizer":[69],"termed":[70],"Hybrid":[71],"Siamese":[72,87,114,127],"Masked":[73,88],"Autoencoders":[74,89],"(H-SMAE)":[75],"higher":[78],"semantic":[79],"perspective.":[80],"Specifically,":[81],"our":[82,181],"method":[83],"consists":[84],"of":[85,137,145,204],"Multi-view":[86],"(MV-SMAE)":[90],"Shot":[92],"Diversity":[93],"Enhancer":[94],"(SDE).":[95],"MV-SMAE":[96,124],"tries":[97],"recover":[99],"masked":[101,115,138],"shots":[102],"original":[104],"feature":[106],"three":[108],"unmasked":[109],"shot":[110],"subsets":[111],"with":[112,196],"elaborate":[113],"autoencoders.":[116],"Inspired":[117],"by":[118,148,163],"masking":[120],"idea":[121],"in":[122],"MAE,":[123],"introduces":[125],"architecture":[128],"model":[130],"prior":[131],"references":[132],"guide":[134],"reconstruction":[136],"shots.":[139,155],"Besides,":[140],"SDE":[141],"improves":[142],"diversity":[144],"generated":[146],"summary":[147],"minimizing":[149],"repelling":[151],"loss":[152],"among":[153],"Afterward,":[156],"these":[157],"two":[158,174],"modules":[159],"fused":[161],"followed":[162],"0-1":[164],"knapsack":[165],"algorithm":[166],"produce":[168],"Experiments":[172],"challenging":[175],"diverse":[177],"datasets":[178],"demonstrate":[179],"that":[180],"approach":[182],"outperforms":[183],"other":[184],"state-of-":[185],"the-art":[186],"weakly-supervised":[189],"even":[192],"generates":[193],"comparable":[194],"results":[195],"several":[197],"excellent":[198],"supervised":[199],"methods.":[200],"The":[201],"code":[203],"H-SMAE":[205],"available":[207],"at":[208],"https://github.com/wzq0214/H-SMAE.":[209]},"counts_by_year":[],"updated_date":"2026-02-20T08:17:22.645390","created_date":"2025-10-10T00:00:00"}