{"id":"https://openalex.org/W4319300227","doi":"https://doi.org/10.1109/wacv56688.2023.00554","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","display_name":"Progressive Video Summarization via Multimodal Self-supervised Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319300227","doi":"https://doi.org/10.1109/wacv56688.2023.00554"},"language":"en","primary_location":{"id":"doi:10.1109/wacv56688.2023.00554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv56688.2023.00554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607736","display_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/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":["The University of Melbourne,School of Computing and Information Systems","School of Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,School of Computing and Information Systems","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne","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/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":["Monash University,Department of Data Science & AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Department of Data Science & AI","institution_ids":["https://openalex.org/I56590836"]}]},{"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":["The University of Melbourne,School of Mathematics and Statistics","School of Mathematics and Statistics, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,School of Mathematics and Statistics","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"School of Mathematics and Statistics, The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017469047","display_name":"Tom Drummond","orcid":"https://orcid.org/0000-0001-8204-5904"},"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":"Tom Drummond","raw_affiliation_strings":["The University of Melbourne,School of Computing and Information Systems","School of Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,School of Computing and Information Systems","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5028,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97525289,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5573","last_page":"5582"},"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":0.9976000189781189,"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":0.9864000082015991,"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":0.9631294012069702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447463512420654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5953133702278137},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5430616140365601},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5340266227722168},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5030576586723328},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5014095306396484},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4312629997730255},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42161834239959717},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4120490550994873},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37692904472351074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3202507495880127}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9631294012069702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447463512420654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953133702278137},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5430616140365601},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5340266227722168},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5030576586723328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5014095306396484},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4312629997730255},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42161834239959717},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4120490550994873},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37692904472351074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3202507495880127},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv56688.2023.00554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv56688.2023.00554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607736","display_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/333327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/WACV56688.2023.00554.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1924343884","https://openalex.org/W1987366351","https://openalex.org/W2109152179","https://openalex.org/W2111494488","https://openalex.org/W2117539524","https://openalex.org/W2139009685","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2529272619","https://openalex.org/W2550462002","https://openalex.org/W2619697695","https://openalex.org/W2737677090","https://openalex.org/W2766630207","https://openalex.org/W2781922022","https://openalex.org/W2798970487","https://openalex.org/W2888101838","https://openalex.org/W2890052321","https://openalex.org/W2895758197","https://openalex.org/W2896457183","https://openalex.org/W2902616437","https://openalex.org/W2963026017","https://openalex.org/W2963115079","https://openalex.org/W2963749571","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W2965373594","https://openalex.org/W2967038491","https://openalex.org/W2967219836","https://openalex.org/W2981851019","https://openalex.org/W2996428491","https://openalex.org/W2999428529","https://openalex.org/W3023371261","https://openalex.org/W3035265375","https://openalex.org/W3037309139","https://openalex.org/W3091588028","https://openalex.org/W3107128832","https://openalex.org/W3107252718","https://openalex.org/W3108154605","https://openalex.org/W3150815828","https://openalex.org/W3154596443","https://openalex.org/W3171941639","https://openalex.org/W3203711169","https://openalex.org/W4226103007","https://openalex.org/W4246193833","https://openalex.org/W4287107550","https://openalex.org/W6771915120","https://openalex.org/W6780294235","https://openalex.org/W6793736971","https://openalex.org/W6797265648"],"related_works":["https://openalex.org/W2093597205","https://openalex.org/W2389846579","https://openalex.org/W2392495745","https://openalex.org/W132250100","https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W2725657302","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Modern":[0],"video":[1,24,61,114,123],"summarization":[2,25,62,115],"methods":[3],"are":[4,26],"based":[5],"on":[6,100],"deep":[7,34],"neural":[8],"networks":[9],"that":[10,37,104],"require":[11],"a":[12,47,101,112,122],"large":[13],"amount":[14],"of":[15,32,40,56,106,139],"annotated":[16],"data":[17],"for":[18,23],"training.":[19],"However,":[20],"existing":[21],"datasets":[22,42],"small-scale,":[27],"easily":[28],"leading":[29],"to":[30,52,127],"over-fitting":[31],"the":[33,38,60,65,72,76,93,118,135],"models.":[35],"Considering":[36],"annotation":[39],"large-scale":[41],"is":[43,68,98,124],"time-consuming,":[44],"we":[45,110],"propose":[46],"multimodal":[48,96],"self-supervised":[49,66],"learning":[50,67],"framework":[51,97],"obtain":[53],"semantic":[54,73],"representations":[55],"videos,":[57],"which":[58],"benefits":[59],"task.":[63],"Specifically,":[64],"conducted":[69],"by":[70],"exploring":[71],"consistency":[74],"between":[75],"videos":[77],"and":[78,83,137,146],"text":[79],"in":[80,92,121,142],"both":[81],"coarse-grained":[82],"fine-grained":[84],"fashions,":[85],"as":[86,88],"well":[87],"recovering":[89],"masked":[90],"frames":[91],"videos.":[94],"The":[95],"trained":[99],"newly-collected":[102],"dataset":[103],"consists":[105],"video-text":[107],"pairs.":[108],"Additionally,":[109],"introduce":[111],"progressive":[113],"method,":[116],"where":[117],"important":[119],"content":[120],"pinpointed":[125],"progressively":[126],"generate":[128],"better":[129],"summaries.":[130],"Extensive":[131],"experiments":[132],"have":[133],"proved":[134],"effectiveness":[136],"superiority":[138],"our":[140],"method":[141],"rank":[143],"correlation":[144],"coefficients":[145],"F-score1.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":7}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}