{"id":"https://openalex.org/W4416183699","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223357","title":"Memory-Augmented Long Short-Term Memory for Dynamic Video Summarization","display_name":"Memory-Augmented Long Short-Term Memory for Dynamic Video Summarization","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4416183699","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223357"},"language":null,"primary_location":{"id":"doi:10.1109/sibgrapi67909.2025.11223357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","raw_type":"proceedings-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/A5049366278","display_name":"Leonardo Vilela Cardoso","orcid":"https://orcid.org/0000-0003-0365-6403"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Leonardo Vilela Cardoso","raw_affiliation_strings":["Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119296218","display_name":"Barbara Hellen P. Soraggi","orcid":null},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Barbara H. P. Soraggi","raw_affiliation_strings":["Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070629635","display_name":"Silvio Jamil F. Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-8522-2056"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Silvio Jamil F. Guimar\u00e3es","raw_affiliation_strings":["Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil","institution_ids":["https://openalex.org/I170935008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035002611","display_name":"Zenilton K. G. Patroc\u00ednio","orcid":"https://orcid.org/0000-0003-0804-1790"},"institutions":[{"id":"https://openalex.org/I170935008","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica de Minas Gerais","ror":"https://ror.org/03j1rr444","country_code":"BR","type":"education","lineage":["https://openalex.org/I170935008"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zenilton K. G. Patroc\u00ednio","raw_affiliation_strings":["Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Image and Multimedia Data Science (IMScience), Pontifical Catholic University of Minas Gerais (PUC Minas),Belo Horizonte,Brazil","institution_ids":["https://openalex.org/I170935008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049366278"],"corresponding_institution_ids":["https://openalex.org/I170935008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3684728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7718999981880188,"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":0.7718999981880188,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1096000000834465,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.031099999323487282,"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":0.9117000102996826},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4237000048160553},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.40459999442100525},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.36320000886917114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3521000146865845},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.33379998803138733},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9117000102996826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.2906999886035919},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sibgrapi67909.2025.11223357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2256670945","https://openalex.org/W2908469318","https://openalex.org/W2964158702","https://openalex.org/W2964167369","https://openalex.org/W2967219836","https://openalex.org/W3169578923","https://openalex.org/W3201625964","https://openalex.org/W3210592264","https://openalex.org/W4226103007","https://openalex.org/W4246193833","https://openalex.org/W4283069582","https://openalex.org/W4288090889","https://openalex.org/W4308842366","https://openalex.org/W4318559722","https://openalex.org/W4319300227","https://openalex.org/W4386453740","https://openalex.org/W4387249902","https://openalex.org/W4388115609","https://openalex.org/W4403535111","https://openalex.org/W4404555350","https://openalex.org/W4405363800","https://openalex.org/W4407448694","https://openalex.org/W4413185497"],"related_works":[],"abstract_inverted_index":{"Capturing":[0],"relevant":[1],"content":[2],"from":[3],"videos":[4],"while":[5,126],"preserving":[6],"temporal":[7,68,129],"coherence":[8],"remains":[9],"a":[10,89,105,133,178,211],"central":[11,36],"challenge":[12],"in":[13,47],"video":[14,49,218],"skimming.":[15],"The":[16],"prevalence":[17],"of":[18,25,38,141,150,183,195],"redundant":[19],"information":[20],"often":[21,53],"hinders":[22],"the":[23,30,35,39,80,120,139,157,175,198],"extraction":[24],"meaningful":[26],"content,":[27,50],"especially":[28],"when":[29,169],"goal":[31],"is":[32],"to":[33,62,66,113,122],"retain":[34],"narrative":[37],"video.":[40],"While":[41],"scene":[42],"change":[43],"detection":[44],"can":[45],"aid":[46],"segmenting":[48],"conventional":[51],"methods":[52],"struggle":[54],"with":[55,172],"highly":[56],"diverse":[57],"and":[58,70,116,160,190,213,223],"repetitive":[59],"scenes":[60],"due":[61],"their":[63],"limited":[64],"ability":[65],"model":[67,121,176],"dependencies":[69],"detect":[71],"transitions":[72],"effectively.":[73],"To":[74],"address":[75],"these":[76],"limitations,":[77],"we":[78],"propose":[79],"Memory-Augmented":[81],"LSTM":[82],"for":[83,201,216],"Dynamic":[84],"Video":[85],"Summarization":[86],"-":[87],"MALSumm,":[88],"supervised":[90,166],"architecture":[91],"based":[92],"on":[93,156,162],"Extended":[94],"Long":[95],"Short-Term":[96],"Memory":[97],"(xLSTM)":[98],"networks":[99],"that":[100,207],"enhances":[101],"memory":[102,112],"capacity":[103],"through":[104],"dual-path":[106],"design.":[107],"This":[108],"design":[109],"integrates":[110],"weighted":[111],"evaluate":[114],"local":[115],"global":[117],"information,":[118],"allowing":[119],"preserve":[123],"fine-grained":[124],"details":[125],"maintaining":[127],"overall":[128],"consistency,":[130],"all":[131],"within":[132],"low-complexity":[134],"framework.":[135],"Experimental":[136],"Results":[137],"validate":[138],"effectiveness":[140],"our":[142,208],"approach,":[143],"achieving":[144],"an":[145],"average":[146],"<tex":[147,151,180,184,192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148,152,181,185,193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{F}$</tex>-score":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{4":[153],"9.":[154],"7}$</tex>":[155],"SumMe":[158],"dataset":[159],"62.1":[161],"TVSum,":[163],"outperforming":[164],"recent":[165],"baselines.":[167],"Additionally,":[168],"measuring":[170],"alignment":[171],"human":[173,202],"annotations,":[174],"attains":[177],"Kendall's":[179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\tau$</tex>":[182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{0.":[186],"1":[187],"8":[188],"0}$</tex>":[189],"Spearman's":[191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\rho$</tex>":[194],"0.242,":[196],"exceeding":[197],"scores":[199],"reported":[200],"agreement.":[203],"These":[204],"findings":[205],"demonstrate":[206],"method":[209],"provides":[210],"competitive":[212],"lightweight":[214],"solution":[215],"dynamic":[217],"summarization,":[219],"effectively":[220],"balancing":[221],"accuracy":[222],"efficiency.":[224]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-11T00:00:00"}