{"id":"https://openalex.org/W4407129945","doi":"https://doi.org/10.1109/cbmi62980.2024.10859210","title":"Toolchain for Comprehensive Audio/Video Analysis Using Deep Learning Based Multimodal Approach: Use Case of Riot or Violent Context Detection","display_name":"Toolchain for Comprehensive Audio/Video Analysis Using Deep Learning Based Multimodal Approach: Use Case of Riot or Violent Context Detection","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4407129945","doi":"https://doi.org/10.1109/cbmi62980.2024.10859210"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi62980.2024.10859210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","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/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,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705490","display_name":"Tin Nguyen","orcid":"https://orcid.org/0009-0008-5041-3627"},"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":"Tin Nguyen","raw_affiliation_strings":["HCM University of Technology,Ho Chi Minh city,Vietnam"],"affiliations":[{"raw_affiliation_string":"HCM University of Technology,Ho Chi Minh city,Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056967532","display_name":"Phat Lam","orcid":"https://orcid.org/0009-0003-5105-5976"},"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":"Phat Lam","raw_affiliation_strings":["HCM University of Technology,Ho Chi Minh city,Vietnam"],"affiliations":[{"raw_affiliation_string":"HCM University of Technology,Ho Chi Minh city,Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082199118","display_name":"Hieu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hieu Tang","raw_affiliation_strings":["FPT University,Ho Chi Minh city,Vietnam"],"affiliations":[{"raw_affiliation_string":"FPT University,Ho Chi Minh city,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102746568","display_name":"Alexander Schindler","orcid":"https://orcid.org/0000-0001-6058-7753"},"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,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075250567"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37795743,"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":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13161","display_name":"Ideological and Political Education","score":0.16419999301433563,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13161","display_name":"Ideological and Political Education","score":0.16419999301433563,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14042","display_name":"Technology and Security Systems","score":0.14300000667572021,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/toolchain","display_name":"Toolchain","score":0.9737437963485718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223314046859741},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6481236219406128},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49621158838272095},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.47174012660980225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.455160528421402},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.40538138151168823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4011211395263672},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39103299379348755},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1495521366596222},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08245602250099182},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.06182658672332764}],"concepts":[{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.9737437963485718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223314046859741},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6481236219406128},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49621158838272095},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.47174012660980225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.455160528421402},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.40538138151168823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4011211395263672},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39103299379348755},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1495521366596222},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08245602250099182},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.06182658672332764},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi62980.2024.10859210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2129795158","https://openalex.org/W2949298458","https://openalex.org/W2990730805","https://openalex.org/W3001434439","https://openalex.org/W3094550259","https://openalex.org/W3096609285","https://openalex.org/W3104862079","https://openalex.org/W3161541317","https://openalex.org/W3217340782","https://openalex.org/W4248034423","https://openalex.org/W4303444955","https://openalex.org/W4311681683","https://openalex.org/W4381854917","https://openalex.org/W4390446623","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3135871143","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W296599067","https://openalex.org/W2020966186","https://openalex.org/W2119339729","https://openalex.org/W4387698063","https://openalex.org/W27741130"],"abstract_inverted_index":{"In":[0],"this":[1,20],"paper,":[2],"we":[3],"present":[4],"a":[5,8,87,100],"toolchain":[6,72,98],"for":[7,112],"comprehensive":[9,83],"audio/video":[10,81,84],"analysis":[11],"by":[12],"leveraging":[13],"deep":[14],"learning":[15],"based":[16],"multimodal":[17],"approach.":[18],"To":[19],"end,":[21],"different":[22],"specific":[23,88],"tasks":[24,59],"of":[25,80,90],"Speech":[26],"to":[27,108],"Text":[28],"(S2T),":[29],"Acoustic":[30,34],"Scene":[31],"Classification":[32],"(ASC),":[33],"Event":[35],"Detection":[36,40],"(AED),":[37],"Visual":[38],"Object":[39],"(VOD),":[41],"Image":[42],"Captioning":[43,47],"(IC),":[44],"and":[45,51,60,86,102],"Video":[46],"(VC)":[48],"are":[49],"conducted":[50],"integrated":[52],"into":[53],"the":[54,71,97],"toolchain.":[55],"By":[56],"combining":[57],"individual":[58],"analyzing":[61],"both":[62],"audio":[63],"&":[64],"visual":[65],"data":[66],"extracted":[67],"from":[68],"input":[69],"video,":[70],"offers":[73],"various":[74],"audio/video-based":[75,114],"applications:":[76],"Two":[77],"general":[78],"applications":[79],"clustering,":[82],"summary":[85],"application":[89],"riot":[91],"or":[92],"violent":[93],"context":[94],"detection.":[95],"Furthermore,":[96],"presents":[99],"flexible":[101],"adaptable":[103],"architecture":[104],"that":[105],"is":[106],"effective":[107],"integrate":[109],"new":[110],"models":[111],"further":[113],"applications.":[115]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
