{"id":"https://openalex.org/W4303444955","doi":"https://doi.org/10.1145/3549555.3549568","title":"An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification","display_name":"An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification","publication_year":2022,"publication_date":"2022-09-14","ids":{"openalex":"https://openalex.org/W4303444955","doi":"https://doi.org/10.1145/3549555.3549568"},"language":"en","primary_location":{"id":"doi:10.1145/3549555.3549568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/10.1145/3549555.3549568","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":["Center for Digital Safety and Security, Austrian Institute of Technology (AIT), Austria"],"affiliations":[{"raw_affiliation_string":"Center for Digital Safety and Security, Austrian Institute of Technology (AIT), Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"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":["Computer Science and Electronic Engineering, University of Essex, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Computer Science and Electronic Engineering, University of Essex, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925609","display_name":"Tho Duc Nguyen","orcid":"https://orcid.org/0000-0002-8418-2416"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tho Nguyen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011303321","display_name":"Phu X. Nguyen","orcid":"https://orcid.org/0000-0001-8637-2507"},"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":"Phu Nguyen","raw_affiliation_strings":["Department of Computing Fundamentals, FPT University, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Department of Computing Fundamentals, FPT University, Viet Nam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025226692","display_name":"Truong Hoang","orcid":"https://orcid.org/0000-0002-5930-8144"},"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":"Truong Hoang","raw_affiliation_strings":["-, FPT Software Company Limited, Viet Nam"],"affiliations":[{"raw_affiliation_string":"-, FPT Software Company Limited, Viet Nam","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":["Center for Digital Safety and Security, Austrian Institute of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Digital Safety and Security, Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":4,"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":1.1911,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78060374,"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":"23","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9941999912261963,"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":0.8039018511772156},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7163881659507751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6137123107910156},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5629875659942627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3683788478374481},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34527385234832764},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32979506254196167},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.31838852167129517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039018511772156},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7163881659507751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6137123107910156},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5629875659942627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3683788478374481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34527385234832764},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32979506254196167},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.31838852167129517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3549555.3549568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3549555.3549568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3549555.3549568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3549555.3549568","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5303534605","display_name":null,"funder_award_id":"879705","funder_id":"https://openalex.org/F4320323031","funder_display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft"}],"funders":[{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"},{"id":"https://openalex.org/F4320324004","display_name":"Forskningsr\u00e5det om H\u00e4lsa, Arbetsliv och V\u00e4lf\u00e4rd","ror":"https://ror.org/02d290r06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4303444955.pdf","grobid_xml":"https://content.openalex.org/works/W4303444955.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2052666245","https://openalex.org/W2596356468","https://openalex.org/W2607662938","https://openalex.org/W2963795951","https://openalex.org/W3006130303","https://openalex.org/W3114298706","https://openalex.org/W4300096145","https://openalex.org/W6687152286"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"In":[0],"this":[1,31],"paper,":[2],"we":[3,33],"present":[4],"the":[5,79,96,109],"task":[6],"of":[7,19,40,53,103,112],"audio-visual":[8,37],"scene":[9],"classification":[10,56],"(SC)":[11],"where":[12],"input":[13,66,91],"videos":[14],"are":[15,58,75],"classified":[16],"into":[17],"one":[18],"five":[20,42],"real-life":[21],"crowded":[22,43],"scenes:":[23],"\u2018Riot\u2019,":[24],"\u2018Noise-Street\u2019,":[25],"\u2018Firework-Event\u2019,":[26],"\u2018Music-Event\u2019,":[27],"and":[28,89],"\u2018Sport-Atmosphere\u2019.":[29],"To":[30],"end,":[32],"firstly":[34],"collect":[35],"an":[36,101],"dataset":[38],"(videos)":[39],"these":[41],"contexts":[44],"from":[45,72],"Youtube":[46],"(in-the-wild":[47],"scenes).":[48],"Then,":[49],"a":[50],"wide":[51],"range":[52],"deep":[54,104],"learning":[55,105],"models":[57,74,106],"proposed":[59],"to":[60,77,95],"train":[61],"either":[62],"audio":[63,88],"or":[64],"visual":[65,90],"data":[67],"independently.":[68],"Finally,":[69],"results":[70,85],"obtained":[71],"high-performance":[73],"fused":[76],"achieve":[78,108],"best":[80,110],"accuracy":[81,111],"score.":[82],"Our":[83],"experimental":[84],"indicate":[86],"that":[87],"factors":[92],"independently":[93],"contribute":[94],"SC":[97],"task\u2019s":[98],"performance.":[99],"Notably,":[100],"ensemble":[102],"can":[107],"95.7%.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
