{"id":"https://openalex.org/W4391096953","doi":"https://doi.org/10.1109/lsp.2024.3356910","title":"Violent Video Recognition Based on Global-Local Visual and Audio Contrastive Learning","display_name":"Violent Video Recognition Based on Global-Local Visual and Audio Contrastive Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391096953","doi":"https://doi.org/10.1109/lsp.2024.3356910"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3356910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3356910","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5037194804","display_name":"Zihao Liu","orcid":"https://orcid.org/0000-0002-0917-001X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Liu","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357651","display_name":"Xiaoyu Wu","orcid":"https://orcid.org/0000-0003-3481-7820"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wu","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030965866","display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101148439","display_name":"Yimeng Shang","orcid":"https://orcid.org/0009-0009-9262-2117"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimeng Shang","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037194804"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":3.1276,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9204546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"476","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9915000200271606,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9873999953269958,"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":0.9678999781608582,"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":0.7960292100906372},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.669610857963562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541199266910553},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5050564408302307},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42233872413635254},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4214855432510376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4184996485710144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4064546823501587},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1456632912158966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960292100906372},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.669610857963562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541199266910553},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5050564408302307},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42233872413635254},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4214855432510376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4184996485710144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4064546823501587},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1456632912158966},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3356910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3356910","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8466875031","display_name":null,"funder_award_id":"61801441","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1969914528","https://openalex.org/W2070065978","https://openalex.org/W2194775991","https://openalex.org/W2939271467","https://openalex.org/W2962943250","https://openalex.org/W2963155035","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3016255809","https://openalex.org/W3021654725","https://openalex.org/W3097283600","https://openalex.org/W3112555387","https://openalex.org/W3175300676","https://openalex.org/W3195367236","https://openalex.org/W3209559115","https://openalex.org/W4200506249","https://openalex.org/W4214507759","https://openalex.org/W4285138127","https://openalex.org/W4289927402","https://openalex.org/W4296519302","https://openalex.org/W4297808394","https://openalex.org/W4307715346","https://openalex.org/W4312753781","https://openalex.org/W4312794093","https://openalex.org/W4382318126","https://openalex.org/W4386270229","https://openalex.org/W4386494534","https://openalex.org/W6754048563","https://openalex.org/W6780294235","https://openalex.org/W6791353385","https://openalex.org/W6844194202","https://openalex.org/W6856259911"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,48,61,71],"the":[3,45,62,69,111,129,134,140],"violent":[4,14,18,73,83,114],"recognition":[5,85],"task":[6],"is":[7],"to":[8,68,103],"determine":[9],"whether":[10],"a":[11,57,82],"video":[12,74,115],"contains":[13],"behaviors.":[15],"Given":[16],"that":[17,120],"behavior":[19],"often":[20],"comes":[21],"with":[22],"visual":[23,90],"and":[24,53,64,91,99,109,137],"audio":[25,92],"anomalies,":[26],"multimodal":[27],"approaches":[28],"have":[29,41],"always":[30],"played":[31],"an":[32],"important":[33],"role":[34],"in":[35,56],"this":[36,78],"field.":[37],"However,":[38],"existing":[39],"methods":[40],"been":[42],"limited":[43],"by":[44,126],"insufficient":[46],"utilization":[47],"audio-visual":[49,105],"self-supervised":[50],"semantic":[51,107],"cues":[52],"correlation,":[54],"resulting":[55],"restricted":[58],"representational":[59],"capacity":[60],"network":[63],"low":[65],"generalization":[66],"due":[67],"scarcity":[70],"available":[72],"datasets.":[75],"To":[76],"address":[77],"issue,":[79],"we":[80],"propose":[81],"action":[84],"model":[86,96,123],"based":[87],"on":[88,128,133,139],"global-local":[89],"contrastive":[93,101],"learning.":[94],"Our":[95],"introduces":[97],"global":[98],"local":[100],"objectives":[102],"achieve":[104],"multi-grained":[106],"alignment":[108],"leverage":[110],"correlation":[112],"for":[113],"recognition.":[116],"Experimental":[117],"results":[118],"demonstrate":[119],"our":[121],"proposed":[122],"improves":[124],"state-of-the-art":[125],"2.31%":[127],"VSD":[130],"dataset,":[131,136],"0.71%":[132],"Violent-Flows":[135],"1.43%":[138],"VCD":[141],"dataset.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}