{"id":"https://openalex.org/W4379806224","doi":"https://doi.org/10.1145/3591106.3592288","title":"Escaping local minima in deep reinforcement learning for video summarization","display_name":"Escaping local minima in deep reinforcement learning for video summarization","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806224","doi":"https://doi.org/10.1145/3591106.3592288"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092114883","display_name":"Panagiota Alexoudi","orcid":"https://orcid.org/0009-0008-0417-9315"},"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":true,"raw_author_name":"Panagiota Alexoudi","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0009-0008-0417-9315","affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of 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":["Department of Informatics, Aristotle University of Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0001-5479-0632","affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of 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":["Department of Informatics, Aristotle University of Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0009-0006-7555-8641","affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092114883"],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":0.1172,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37934946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"530","last_page":"534"},"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":0.9977999925613403,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9728999733924866,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8420232534408569},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8063491582870483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7612101435661316},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.721043586730957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6448281407356262},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5920337438583374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49706390500068665},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.4886758625507355},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4813038408756256},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45291540026664734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4478328824043274},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4383096992969513},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43743789196014404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42502692341804504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37906432151794434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08760485053062439}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8420232534408569},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8063491582870483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612101435661316},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.721043586730957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448281407356262},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5920337438583374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49706390500068665},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.4886758625507355},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4813038408756256},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45291540026664734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4478328824043274},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4383096992969513},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43743789196014404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42502692341804504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37906432151794434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08760485053062439},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3591106.3592288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:8341191","is_oa":true,"landing_page_url":"https://zenodo.org/record/8341191","pdf_url":"https://zenodo.org/record/8341191","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":"doi:10.1145/3591106.3592288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1322071649","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4397263494","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379806224.pdf","grobid_xml":"https://content.openalex.org/works/W4379806224.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2529165750","https://openalex.org/W2560835477","https://openalex.org/W2963026017","https://openalex.org/W2963558761","https://openalex.org/W2964158702","https://openalex.org/W2993980108","https://openalex.org/W3010790568","https://openalex.org/W3099156605","https://openalex.org/W3103014337","https://openalex.org/W3140428646","https://openalex.org/W3143835353","https://openalex.org/W3202797049"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2366403280","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W1495108544","https://openalex.org/W4319453655","https://openalex.org/W2623188001","https://openalex.org/W2908469318"],"abstract_inverted_index":{"State-of-the-art":[0],"deep":[1],"neural":[2,133],"unsupervised":[3,112],"video":[4,42],"summarization":[5],"methods":[6],"mostly":[7],"fall":[8],"under":[9],"the":[10,74,84,129,132,147,154,176,180],"adversarial":[11],"reconstruction":[12],"framework.":[13],"This":[14,58],"employs":[15],"a":[16,36,78,91,100,123,139,161],"Generative":[17],"Adversarial":[18],"Network":[19],"(GAN)":[20],"structure":[21],"and":[22,45,178],"Long":[23],"Short-Term":[24],"Memory":[25],"(LSTM)":[26],"autoencoders":[27],"during":[28,122],"its":[29],"training":[30,125,148],"stage.":[31],"The":[32],"typical":[33],"result":[34],"is":[35,116],"selector":[37],"LSTM":[38],"that":[39,127],"sequentially":[40],"receives":[41],"frame":[43],"representations":[44],"outputs":[46],"corresponding":[47],"scalar":[48],"importance":[49],"factors,":[50],"which":[51,80],"are":[52,90],"then":[53],"used":[54],"to":[55,82,110,150,159],"select":[56],"key-frames.":[57],"basic":[59],"approach":[60],"has":[61],"been":[62],"augmented":[63],"with":[64],"an":[65,117],"additional":[66],"Deep":[67],"Reinforcement":[68],"Learning":[69],"(DRL)":[70],"agent,":[71],"trained":[72],"using":[73],"Discriminator\u2019s":[75],"output":[76],"as":[77],"reward,":[79],"learns":[81],"optimize":[83],"selector\u2019s":[85],"outputs.":[86],"However,":[87],"local":[88,105,163],"minima":[89],"well-known":[92],"problem":[93],"in":[94,108,157],"DRL.":[95],"Thus,":[96,144],"this":[97],"paper":[98],"presents":[99],"novel":[101],"regularizer":[102],"for":[103],"escaping":[104],"loss":[106,119,164],"minima,":[107],"order":[109,158],"improve":[111],"key-frame":[113],"extraction.":[114],"It":[115],"additive":[118],"term":[120],"employed":[121],"second":[124],"phase,":[126],"rewards":[128],"difference":[130],"of":[131,138],"agent\u2019s":[134],"parameters":[135],"from":[136],"those":[137],"previously":[140],"found":[141],"good":[142],"solution.":[143],"it":[145],"encourages":[146],"process":[149],"explore":[151],"more":[152],"aggressively":[153],"parameter":[155],"space":[156],"discover":[160],"better":[162],"minimum.":[165],"Evaluation":[166],"performed":[167],"on":[168],"two":[169],"public":[170],"datasets":[171],"shows":[172],"considerable":[173],"increases":[174],"over":[175],"baseline":[177],"against":[179],"state-of-the-art.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}