{"id":"https://openalex.org/W4390446623","doi":"https://doi.org/10.1145/3617233.3617248","title":"Deep Learning Based Multimodal with Two-phase Training Strategy for Daily Life Video Classification","display_name":"Deep Learning Based Multimodal with Two-phase Training Strategy for Daily Life Video Classification","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4390446623","doi":"https://doi.org/10.1145/3617233.3617248"},"language":"en","primary_location":{"id":"doi:10.1145/3617233.3617248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","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/10.1145/3617233.3617248","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Austrian Institute of Technology, Austria"],"raw_orcid":"https://orcid.org/0000-0001-8155-7553","affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Trang Le","orcid":"https://orcid.org/0009-0008-9148-2848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trang Le","raw_affiliation_strings":["JVN Institute-VNU, Vietnam"],"raw_orcid":"https://orcid.org/0009-0008-9148-2848","affiliations":[{"raw_affiliation_string":"JVN Institute-VNU, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030642705","display_name":"Cam Le","orcid":"https://orcid.org/0009-0002-8883-4677"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cam Le","raw_affiliation_strings":["HCM University of Technology, Vietnam"],"raw_orcid":"https://orcid.org/0009-0002-8883-4677","affiliations":[{"raw_affiliation_string":"HCM University of Technology, Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968151","display_name":"Dat Ngo","orcid":"https://orcid.org/0000-0003-4374-5056"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dat Ngo","raw_affiliation_strings":["University of Essex, UK"],"raw_orcid":"https://orcid.org/0000-0003-4374-5056","affiliations":[{"raw_affiliation_string":"University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027002971","display_name":"Axel Wei\u00dfenfeld","orcid":"https://orcid.org/0000-0002-7246-2744"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Axel Weissenfeld","raw_affiliation_strings":["AIT Austrian Institute of Technology GmbH, Austria"],"raw_orcid":"https://orcid.org/0000-0002-7246-2744","affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology GmbH, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678930","display_name":"Alexander Schindler","orcid":"https://orcid.org/0000-0002-4881-6741"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexander Schindler","raw_affiliation_strings":["Austrian Institute of Technology, Austria"],"raw_orcid":"https://orcid.org/0000-0002-4881-6741","affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075250567"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.3768,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59136254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"238","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.995199978351593,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.7721171379089355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7138375639915466},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6922016143798828},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6539030075073242},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6537460684776306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5803569555282593},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5194922685623169},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4737069308757782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4697687327861786},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4298834502696991},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42749032378196716},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41450071334838867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37269851565361023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35277730226516724},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09066575765609741},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06434595584869385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721171379089355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7138375639915466},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6922016143798828},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6539030075073242},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6537460684776306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5803569555282593},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5194922685623169},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4737069308757782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4697687327861786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4298834502696991},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42749032378196716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41450071334838867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37269851565361023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35277730226516724},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09066575765609741},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06434595584869385},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617233.3617248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3617233.3617248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3758062707","display_name":null,"funder_award_id":"101021797","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7819451495","display_name":null,"funder_award_id":"101021797","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"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/W4390446623.pdf","grobid_xml":"https://content.openalex.org/works/W4390446623.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1927052826","https://openalex.org/W2117539524","https://openalex.org/W2570915410","https://openalex.org/W2703895418","https://openalex.org/W3090950327","https://openalex.org/W3114298706","https://openalex.org/W3161541317","https://openalex.org/W3161798961","https://openalex.org/W4283754361","https://openalex.org/W4311681683","https://openalex.org/W4312756816","https://openalex.org/W4313483482","https://openalex.org/W4319586559","https://openalex.org/W4360596622"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2271369634","https://openalex.org/W2130974462","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":{"In":[0,26,82],"this":[1],"paper,":[2],"we":[3,20,33,65,89],"present":[4],"a":[5,22,91,100],"deep":[6,57,79],"learning":[7,58,80],"based":[8,59],"multimodal":[9],"system":[10],"for":[11],"classifying":[12],"daily":[13,110],"life":[14],"videos.":[15],"To":[16],"train":[17,47,90],"the":[18,27,35,42,48,52,62,77,83,96,105,119,141,184],"system,":[19],"propose":[21],"two-phase":[23],"training":[24,29,63,85],"strategy.":[25],"first":[28],"phase":[30,86],"(Phase":[31,87],"I),":[32],"extract":[34],"audio":[36,49,67,152,159],"and":[37,51,69,99,129,134,148,160,179],"visual":[38,53,70,156,161],"(image)":[39],"data":[40,50,54],"from":[41,76],"original":[43],"video.":[44],"We":[45],"then":[46],"with":[55,150,154,176],"independent":[56],"models.":[60,81],"After":[61],"processes,":[64],"obtain":[66],"embeddings":[68,71,98],"by":[72],"extracting":[73],"feature":[74],"maps":[75],"pre-trained":[78],"second":[84],"II),":[88],"fusion":[92],"layer":[93,102],"to":[94,103,183],"combine":[95],"audio/visual":[97],"dense":[101],"classify":[104],"combined":[106],"embedding":[107],"into":[108],"target":[109],"scenes.":[111],"Our":[112],"extensive":[113],"experiments,":[114],"which":[115],"were":[116],"conducted":[117],"on":[118,127],"benchmark":[120],"dataset":[121],"of":[122,131,145,168,173],"DCASE":[123,177],"(IEEE":[124],"AASP":[125],"Challenge":[126],"Detection":[128],"Classification":[130],"Acoustic":[132],"Scenes":[133],"Events)":[135],"2021":[136],"Task":[137],"1B":[138],"Development,":[139],"achieved":[140],"best":[142],"classification":[143,166],"accuracy":[144,167],"80.5%,":[146],"91.8%,":[147],"95.3%":[149,169],"only":[151,155],"data,":[153,157,162],"both":[158],"respectively.":[163],"The":[164],"highest":[165],"presents":[170],"an":[171],"improvement":[172],"17.9%":[174],"compared":[175],"baseline":[178],"shows":[180],"very":[181],"competitive":[182],"state-of-the-art":[185],"systems.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}