{"id":"https://openalex.org/W4392904066","doi":"https://doi.org/10.1109/icassp48485.2024.10447086","title":"FCC-MF: Detecting Violence in Audio-Visual Context with Frame-Wise Cluster Contrast and Modality-Stage Flooding","display_name":"FCC-MF: Detecting Violence in Audio-Visual Context with Frame-Wise Cluster Contrast and Modality-Stage Flooding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904066","doi":"https://doi.org/10.1109/icassp48485.2024.10447086"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447086","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002522399","display_name":"Jiaqing He","orcid":"https://orcid.org/0000-0003-3954-6003"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing He","raw_affiliation_strings":["Wuhan University,School of Cyber Science and Engineering","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499462","display_name":"Yanzhen Ren","orcid":"https://orcid.org/0000-0003-0799-5082"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhen Ren","raw_affiliation_strings":["Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education","institution_ids":[]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001446444","display_name":"Liming Zhai","orcid":"https://orcid.org/0000-0003-3229-056X"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Zhai","raw_affiliation_strings":["Central China Normal University,School of Computer Science","School of Computer Science, Central China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,School of Computer Science","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"School of Computer Science, Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049058927","display_name":"Wuyang Liu","orcid":"https://orcid.org/0000-0003-2790-3069"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuyang Liu","raw_affiliation_strings":["Wuhan University,School of Cyber Science and Engineering","School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5557,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68809813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8346","last_page":"8350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937000274658203,"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":0.6768514513969421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6082875728607178},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5761582255363464},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5757599472999573},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5478021502494812},{"id":"https://openalex.org/keywords/flooding","display_name":"Flooding (psychology)","score":0.5176846981048584},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48616477847099304},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.45761436223983765},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.438432514667511},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41961196064949036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3848363161087036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3411374092102051},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11015242338180542},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10183751583099365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6768514513969421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6082875728607178},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5761582255363464},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5757599472999573},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5478021502494812},{"id":"https://openalex.org/C186594467","wikidata":"https://www.wikidata.org/wiki/Q1429176","display_name":"Flooding (psychology)","level":2,"score":0.5176846981048584},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48616477847099304},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.45761436223983765},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.438432514667511},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41961196064949036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3848363161087036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3411374092102051},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11015242338180542},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10183751583099365},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447086","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2105497548","https://openalex.org/W2194775991","https://openalex.org/W2341058432","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2786672974","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2966277378","https://openalex.org/W2966587068","https://openalex.org/W3008189420","https://openalex.org/W3089682612","https://openalex.org/W3118120400","https://openalex.org/W3136793533","https://openalex.org/W3168600998","https://openalex.org/W3175335326","https://openalex.org/W3200038569","https://openalex.org/W3207876826","https://openalex.org/W4225280406","https://openalex.org/W4226206782","https://openalex.org/W4285206108","https://openalex.org/W4292958273","https://openalex.org/W4304083155","https://openalex.org/W4304098292","https://openalex.org/W4312639100","https://openalex.org/W4312723609","https://openalex.org/W4385245566","https://openalex.org/W4386076561","https://openalex.org/W4387934964","https://openalex.org/W6726497184","https://openalex.org/W6734384760","https://openalex.org/W6739901393","https://openalex.org/W6748816842","https://openalex.org/W6774637898","https://openalex.org/W6810452849","https://openalex.org/W6840050339","https://openalex.org/W6841484515"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W627697492"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,60,119,153],"detection":[4,62],"of":[5,8,27,131,139,150],"frame-wise":[6,107],"instances":[7],"violence":[9,174],"in":[10],"both":[11],"audio":[12,43],"and":[13,36,44,55,97,135,177],"visual":[14,45],"modalities,":[15],"where":[16],"only":[17],"clip-level":[18],"labels":[19],"are":[20],"available.":[21],"Previous":[22],"works":[23],"selected":[24],"fixed":[25],"value":[26],"frames":[28,96],"for":[29,94,100,105],"objective":[30],"optimization":[31],"to":[32,41,103,125],"model":[33],"frame-level":[34,173],"features,":[35,127],"applied":[37],"straightforward":[38],"fusion":[39,180],"strategy":[40],"aggregate":[42],"information.":[46,141],"However,":[47],"these":[48,66],"two":[49],"issues,":[50,67],"namely":[51],"Constant":[52],"Frames":[53],"Selection":[54],"Vulnerable":[56],"Fusion,":[57],"significantly":[58],"impair":[59],"network\u2019s":[61],"performance.":[63],"To":[64],"address":[65],"we":[68],"present":[69],"a":[70,114,146],"novel":[71],"framework":[72,144,170],"called":[73],"Frame-wise":[74,87],"Cluster":[75,88],"Contrast":[76],"with":[77,118],"Modality-stage":[78,112],"Flooding":[79],"(FCC-MF).":[80],"Our":[81,142],"contributions":[82],"include:":[83],"1)":[84],"We":[85,110],"propose":[86,111],"Contrast,":[89],"which":[90,128,156],"leverages":[91],"unsupervised":[92],"clustering":[93],"pseudo-labeling":[95],"triplet":[98],"loss":[99,121],"contrastive":[101],"learning":[102],"allow":[104],"dynamic":[106],"discrimination.":[108],"2)":[109],"Flooding,":[113],"two-stage":[115],"flooding":[116,122],"approach":[117],"higher":[120],"level":[123],"assigned":[124],"uni-modal":[126,133],"prevents":[129],"over-memorization":[130],"redundant":[132],"data":[134],"promotes":[136],"effective":[137],"aggregation":[138],"multi-modal":[140],"FCC-MF":[143,169],"yields":[145],"promising":[147],"average":[148],"precision":[149],"84.24%":[151],"on":[152],"XD-Violence":[154],"dataset,":[155],"performs":[157],"favorably":[158],"against":[159],"previous":[160],"SOTA":[161],"methods.":[162],"Extensive":[163],"ablation":[164],"studies":[165],"exhibit":[166],"that":[167],"our":[168],"produces":[171],"finer":[172],"discrimination":[175],"ability":[176],"generalizable":[178],"audio-visual":[179],"features.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}