{"id":"https://openalex.org/W4226103007","doi":"https://doi.org/10.1109/tpami.2022.3186506","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","display_name":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226103007","doi":"https://doi.org/10.1109/tpami.2022.3186506","pmid":"https://pubmed.ncbi.nlm.nih.gov/35759594"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3186506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3186506","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.13478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101639297","display_name":"Haopeng Li","orcid":"https://orcid.org/0000-0001-8175-5381"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haopeng Li","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8175-5381","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083239184","display_name":"Qiuhong Ke","orcid":"https://orcid.org/0000-0001-9998-3614"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiuhong Ke","raw_affiliation_strings":["Department of Data Science & AI, Monash University and the School of Computing and Information Systems, University of Melbourne, Australia","Department of Data Science &amp"],"raw_orcid":"https://orcid.org/0000-0001-9998-3614","affiliations":[{"raw_affiliation_string":"Department of Data Science & AI, Monash University and the School of Computing and Information Systems, University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I56590836"]},{"raw_affiliation_string":"Department of Data Science &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102023771","display_name":"Mingming Gong","orcid":"https://orcid.org/0000-0001-7147-5589"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["School of Mathematics and Statistics, University of Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7147-5589","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250"},"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":"Rui Zhang","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-8132-6250","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1713,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93396393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"45","issue":"3","first_page":"1","last_page":"14"},"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":0.9904000163078308,"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":0.9750999808311462,"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":0.9397872686386108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8675376176834106},{"id":"https://openalex.org/keywords/storyboard","display_name":"Storyboard","score":0.7446869611740112},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5855918526649475},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5840100646018982},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5622907876968384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5470569133758545},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4217653274536133},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3361778259277344},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3312101662158966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32692205905914307},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.25741255283355713}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9397872686386108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675376176834106},{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.7446869611740112},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5855918526649475},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5840100646018982},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5622907876968384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5470569133758545},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4217653274536133},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3361778259277344},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3312101662158966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32692205905914307},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25741255283355713},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2022.3186506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3186506","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35759594","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35759594","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2112.13478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.13478","pdf_url":"https://arxiv.org/pdf/2112.13478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.13478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.13478","pdf_url":"https://arxiv.org/pdf/2112.13478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1924343884","https://openalex.org/W1926243429","https://openalex.org/W1987366351","https://openalex.org/W2016053056","https://openalex.org/W2062903088","https://openalex.org/W2097117768","https://openalex.org/W2109152179","https://openalex.org/W2111494488","https://openalex.org/W2117539524","https://openalex.org/W2139009685","https://openalex.org/W2194775991","https://openalex.org/W2338907589","https://openalex.org/W2529272619","https://openalex.org/W2560681555","https://openalex.org/W2607326921","https://openalex.org/W2737677090","https://openalex.org/W2766630207","https://openalex.org/W2781922022","https://openalex.org/W2798970487","https://openalex.org/W2895758197","https://openalex.org/W2896457183","https://openalex.org/W2902616437","https://openalex.org/W2908469318","https://openalex.org/W2946527862","https://openalex.org/W2962898677","https://openalex.org/W2963026017","https://openalex.org/W2963563276","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W2964167369","https://openalex.org/W2967038491","https://openalex.org/W2967219836","https://openalex.org/W2972712288","https://openalex.org/W2982672255","https://openalex.org/W2993980108","https://openalex.org/W2999428529","https://openalex.org/W3035029089","https://openalex.org/W3045623285","https://openalex.org/W3085139254","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3103358580","https://openalex.org/W3107252718","https://openalex.org/W3108154605","https://openalex.org/W3112815474","https://openalex.org/W3135176014","https://openalex.org/W3150815828","https://openalex.org/W3172837290","https://openalex.org/W4246193833","https://openalex.org/W4287667694","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6780226713","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W1574724839","https://openalex.org/W4221117092","https://openalex.org/W2213155192","https://openalex.org/W1623638113","https://openalex.org/W2096476311","https://openalex.org/W181787362","https://openalex.org/W2406608628","https://openalex.org/W3034776505","https://openalex.org/W2899854151","https://openalex.org/W2746669491"],"abstract_inverted_index":{"Video":[0,59],"summarization":[1,30,126],"aims":[2],"to":[3,107,137,153],"automatically":[4],"generate":[5],"a":[6,13],"summary":[7,144],"(storyboard":[8],"or":[9],"video":[10,19,29,48,51,104,132],"skim)":[11],"of":[12,24,81,84,95,127,157,164,168],"video,":[14],"which":[15,34,69],"can":[16],"facilitate":[17],"large-scale":[18],"retrieval":[20],"and":[21,50,122,145,161,170],"browsing.":[22],"Most":[23],"the":[25,36,73,86,99,125,139,143,146,155,158,162],"existing":[26],"methods":[27],"perform":[28],"on":[31,63],"individual":[32,93,128],"videos,":[33,97],"neglects":[35],"correlations":[37],"among":[38],"similar":[39,96],"videos.":[40,77,129],"Such":[41],"correlations,":[42],"however,":[43],"are":[44,119,151],"also":[45],"informative":[46],"for":[47,67,124],"understanding":[49],"summarization.":[52],"To":[53],"address":[54],"this":[55,113],"limitation,":[56],"we":[57],"propose":[58],"Joint":[60],"Modelling":[61],"based":[62],"Hierarchical":[64],"Transformer":[65],"(VJMHT)":[66],"co-summarization,":[68],"takes":[70],"into":[71],"consideration":[72],"semantic":[74,90,110],"dependencies":[75],"across":[76],"Specifically,":[78],"VJMHT":[79,165],"consists":[80],"two":[82],"layers":[83],"Transformer:":[85],"first":[87],"layer":[88,101],"extracts":[89],"representation":[91,133],"from":[92],"shots":[94],"while":[98],"second":[100],"performs":[102],"shot-level":[103],"joint":[105],"modelling":[106],"aggregate":[108],"cross-video":[109,116],"information.":[111],"By":[112],"means,":[114],"complete":[115],"high-level":[117,140],"patterns":[118],"explicitly":[120],"modelled":[121],"learned":[123],"Moreover,":[130],"Transformer-based":[131],"reconstruction":[134],"is":[135],"introduced":[136],"maximize":[138],"similarity":[141],"between":[142],"original":[147],"video.":[148],"Extensive":[149],"experiments":[150],"conducted":[152],"verify":[154],"effectiveness":[156],"proposed":[159],"modules":[160],"superiority":[163],"in":[166],"terms":[167],"F-measure":[169],"rank-based":[171],"evaluation.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}