{"id":"https://openalex.org/W4224920450","doi":"https://doi.org/10.1109/icassp43922.2022.9747592","title":"Exploiting Caption Diversity for Unsupervised Video Summarization","display_name":"Exploiting Caption Diversity for Unsupervised Video Summarization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920450","doi":"https://doi.org/10.1109/icassp43922.2022.9747592"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747592","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/ICASSP43922.2022.9747592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033926276","display_name":"Michail Kaseris","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Michail Kaseris","raw_affiliation_strings":["Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070716976","display_name":"Ioannis Mademlis","orcid":"https://orcid.org/0000-0001-5479-0632"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Mademlis","raw_affiliation_strings":["Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061130224","display_name":"Ioannis Pitas","orcid":"https://orcid.org/0009-0006-7555-8641"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Pitas","raw_affiliation_strings":["Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":0.4719,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72171753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1650","last_page":"1654"},"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":0.9957000017166138,"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":0.9926999807357788,"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":0.8769336938858032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8624324202537537},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6653846502304077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6591988801956177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5972227454185486},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5799562335014343},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5756667852401733},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.532941460609436},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5129175186157227},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.467912495136261},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.42784371972084045},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41189634799957275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3672747313976288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3587573170661926}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8769336938858032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8624324202537537},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6653846502304077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591988801956177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5972227454185486},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5799562335014343},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5756667852401733},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.532941460609436},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5129175186157227},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.467912495136261},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.42784371972084045},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41189634799957275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3672747313976288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587573170661926},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747592","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:10036186","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP43922.2022.9747592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10036186","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP43922.2022.9747592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W1987366351","https://openalex.org/W2139009685","https://openalex.org/W2529165750","https://openalex.org/W2529272619","https://openalex.org/W2531212856","https://openalex.org/W2737677090","https://openalex.org/W2754559068","https://openalex.org/W2774624877","https://openalex.org/W2802674542","https://openalex.org/W2899269241","https://openalex.org/W2903758693","https://openalex.org/W2964158702","https://openalex.org/W2967038491","https://openalex.org/W2982672255","https://openalex.org/W2984001224","https://openalex.org/W2993980108","https://openalex.org/W2997333136","https://openalex.org/W3010790568","https://openalex.org/W3103014337","https://openalex.org/W3195810384","https://openalex.org/W4292928772","https://openalex.org/W4320013936","https://openalex.org/W6640109428","https://openalex.org/W6681240974","https://openalex.org/W6728272395","https://openalex.org/W6751495912","https://openalex.org/W6774800999","https://openalex.org/W6981526023"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2366403280","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W3046127589","https://openalex.org/W4287704324","https://openalex.org/W3093409497","https://openalex.org/W2908469318"],"abstract_inverted_index":{"Most":[0],"unsupervised":[1],"Deep":[2],"Neural":[3,26],"Networks":[4],"(DNNs)":[5],"for":[6],"video":[7,29,53],"summarization":[8],"rely":[9],"on":[10],"adversarial":[11],"learning,":[12],"autoencoding":[13],"and":[14],"training":[15],"without":[16],"utilizing":[17],"any":[18],"ground-truth":[19],"summary.":[20],"In":[21,85],"several":[22],"cases,":[23],"the":[24,51,55,68,78,110,117,153],"Convolutional":[25],"Network":[27],"(CNN)-derived":[28],"frame":[30],"representations":[31],"are":[32,120],"sequentially":[33],"fed":[34],"to":[35,49,103,122,128,137,157],"a":[36,88,96],"Long":[37],"Short-Term":[38],"Memory":[39],"(LSTM)":[40],"network,":[41],"which":[42,141],"selects":[43],"key-frames":[44,119],"and,":[45],"during":[46],"training,":[47],"attempts":[48],"reconstruct":[50],"original/full":[52],"from":[54,109],"summary,":[56],"while":[57],"confusing":[58],"an":[59],"adversarially":[60],"optimized":[61],"Discriminator.":[62],"Additionally,":[63],"regularizers":[64],"aiming":[65],"at":[66],"maximizing":[67],"summary\u2019s":[69],"visual":[70],"semantic":[71,114],"diversity":[72,108],"can":[73],"be":[74],"employed,":[75],"such":[76],"as":[77],"Determinantal":[79],"Point":[80],"Process":[81],"(DPP)":[82],"loss":[83],"term.":[84],"this":[86],"paper,":[87],"novel":[89],"DPP-based":[90],"regularizer":[91,155],"is":[92],"proposed":[93,154],"that":[94,152],"exploits":[95],"pretrained":[97],"DNN-based":[98],"image":[99],"captioner":[100],"in":[101],"order":[102],"additionally":[104,143],"enforce":[105],"maximal":[106],"key-frame":[107],"perspective":[111],"of":[112],"textual":[113,139],"content.":[115],"Thus,":[116],"selected":[118],"encouraged":[121],"differ":[123],"not":[124],"only":[125],"with":[126,135],"regard":[127,136],"what":[129],"objects":[130],"they":[131],"depict,":[132],"but":[133],"also":[134],"their":[138],"descriptions,":[140],"may":[142],"capture":[144],"activities,":[145],"scene":[146],"context,":[147],"etc.":[148],"Empirical":[149],"evaluation":[150],"indicates":[151],"leads":[156],"state-of-the-art":[158],"performance.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}