{"id":"https://openalex.org/W3160045550","doi":"https://doi.org/10.1109/icassp39728.2021.9413686","title":"Violence Detection in Videos Based on Fusing Visual and Audio Information","display_name":"Violence Detection in Videos Based on Fusing Visual and Audio Information","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160045550","doi":"https://doi.org/10.1109/icassp39728.2021.9413686","mag":"3160045550"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5011018489","display_name":"Wenfeng Pang","orcid":"https://orcid.org/0000-0002-9443-7208"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-Feng Pang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian-Hua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772000","display_name":"Yongjian Hu","orcid":"https://orcid.org/0000-0002-7775-3786"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-jian Hu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan-Xiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2260","last_page":"2264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.996399998664856,"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":0.8232372403144836},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7074498534202576},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6577767133712769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386735439300537},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5050612092018127},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4591389000415802},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4049566388130188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3382103145122528},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.198182612657547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232372403144836},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7074498534202576},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6577767133712769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386735439300537},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5050612092018127},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4591389000415802},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4049566388130188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3382103145122528},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.198182612657547}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6000000238418579,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1821462560","https://openalex.org/W1921523184","https://openalex.org/W1952703253","https://openalex.org/W1969914528","https://openalex.org/W2054888992","https://openalex.org/W2070065978","https://openalex.org/W2101664593","https://openalex.org/W2105497548","https://openalex.org/W2120738856","https://openalex.org/W2160850850","https://openalex.org/W2341058432","https://openalex.org/W2519887557","https://openalex.org/W2526050071","https://openalex.org/W2620998106","https://openalex.org/W2914914601","https://openalex.org/W2935858441","https://openalex.org/W2949197413","https://openalex.org/W2962756039","https://openalex.org/W2962795401","https://openalex.org/W2962943250","https://openalex.org/W2963066927","https://openalex.org/W2963091558","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2964015378","https://openalex.org/W2964121744","https://openalex.org/W2971680695","https://openalex.org/W2979157532","https://openalex.org/W3089682612","https://openalex.org/W4293665662","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6640185926","https://openalex.org/W6675613107","https://openalex.org/W6726873649","https://openalex.org/W6728881024","https://openalex.org/W6729831399","https://openalex.org/W6759825117"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Determining":[0],"whether":[1],"given":[2],"video":[3],"frames":[4],"contain":[5],"violent":[6],"content":[7],"is":[8],"a":[9,26,58,125],"basic":[10],"problem":[11],"in":[12,25],"violence":[13,23,33],"detection.":[14],"Visual":[15],"and":[16,28,40,53,86,98,107],"audio":[17,41,54,87,99],"information":[18,42,100,119],"are":[19,29,43],"useful":[20],"for":[21,50,64,71,92,112],"detecting":[22],"included":[24],"video,":[27],"usually":[30],"complementary;":[31],"however,":[32],"detection":[34],"studies":[35],"focusing":[36],"on":[37,80,102,140],"fusing":[38,51,65,96],"visual":[39,52,85,97,118],"relatively":[44],"rare.":[45],"Therefore,":[46],"we":[47],"explored":[48],"methods":[49,139],"information.":[55],"We":[56],"proposed":[57,133],"neural":[59,122,134],"network":[60,123,135],"containing":[61],"three":[62],"modules":[63],"multimodal":[66],"information:":[67],"1)":[68],"attention":[69],"module":[70,91,111],"utilizing":[72],"weighted":[73],"features":[74,78,94],"to":[75,116],"generate":[76],"effective":[77],"based":[79,101],"the":[81,103,114,132,141],"mutual":[82,109],"guidance":[83],"between":[84],"information;":[88],"2)":[89],"fusion":[90],"integrating":[93],"by":[95],"bilinear":[104],"pooling":[105],"mechanism;":[106],"3)":[108],"Learning":[110],"enabling":[113],"model":[115],"learn":[117],"from":[120],"another":[121],"with":[124],"different":[126],"architecture.":[127],"Experimental":[128],"results":[129],"indicated":[130],"that":[131],"outperforms":[136],"existing":[137],"state-of-the-art":[138],"XD-Violence":[142],"dataset.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}