{"id":"https://openalex.org/W4304098292","doi":"https://doi.org/10.1145/3503161.3547868","title":"Modality-aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","display_name":"Modality-aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098292","doi":"https://doi.org/10.1145/3503161.3547868"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547868","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5052798964","display_name":"Jiashuo Yu","orcid":"https://orcid.org/0000-0002-3094-6687"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiashuo Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329175","display_name":"Jinyu Liu","orcid":"https://orcid.org/0000-0002-1799-019X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Liu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060790908","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-9103-6126"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052798964"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":4.1831,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95457677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6278","last_page":"6287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9922000169754028,"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":0.9901999831199646,"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":0.7737876176834106},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7039145231246948},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6605334281921387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6051342487335205},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5693773627281189},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4629474878311157},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4279508888721466},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4254021942615509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36925065517425537},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1050700843334198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737876176834106},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7039145231246948},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6605334281921387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051342487335205},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5693773627281189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4629474878311157},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4279508888721466},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4254021942615509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36925065517425537},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1050700843334198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547868","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6800000071525574,"display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G6158060843","display_name":null,"funder_award_id":"No. 21511101000, No. 21511100602","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2024016554","https://openalex.org/W2187089797","https://openalex.org/W2294370754","https://openalex.org/W2341058432","https://openalex.org/W2463402750","https://openalex.org/W2541102286","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2798991696","https://openalex.org/W2809440904","https://openalex.org/W2939271467","https://openalex.org/W2962709777","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963524571","https://openalex.org/W2963610939","https://openalex.org/W2963795951","https://openalex.org/W2970271202","https://openalex.org/W2987850001","https://openalex.org/W3016255809","https://openalex.org/W3035060554","https://openalex.org/W3035160371","https://openalex.org/W3035524453","https://openalex.org/W3048939150","https://openalex.org/W3089682612","https://openalex.org/W3099638501","https://openalex.org/W3118120400","https://openalex.org/W3134566480","https://openalex.org/W3136793533","https://openalex.org/W3159481202","https://openalex.org/W3162322471","https://openalex.org/W3168600998","https://openalex.org/W3173178959","https://openalex.org/W3175300676","https://openalex.org/W3176403475","https://openalex.org/W3190580390","https://openalex.org/W3201703290","https://openalex.org/W4214653736","https://openalex.org/W4220798700"],"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/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Weakly-supervised":[0],"audio-visual":[1,19,65,155],"violence":[2,10],"detection":[3],"aims":[4],"to":[5,90,148,153,199],"distinguish":[6],"snippets":[7],"containing":[8],"multimodal":[9,168],"events":[11],"with":[12,78,129,178],"video-level":[13],"labels.":[14],"Many":[15],"prior":[16],"works":[17],"perform":[18],"integration":[20],"and":[21,46,57,93,101,114,124,131,160,167],"interaction":[22],"in":[23,96,108,134],"an":[24,109],"early":[25],"or":[26],"intermediate":[27],"manner,":[28],"yet":[29],"overlooking":[30],"the":[31,35,43,51,135,154,162,182],"modality":[32,44,137],"heterogeneousness":[33],"over":[34],"weakly-supervised":[36,64],"setting.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,71,84],"analyze":[42],"asynchrony":[45],"undifferentiated":[47],"instances":[48,103,133],"phenomena":[49],"of":[50],"multiple":[52],"instance":[53,76],"learning":[54,77],"(MIL)":[55],"procedure,":[56],"further":[58],"investigate":[59],"its":[60],"negative":[61,140],"impact":[62],"on":[63,181],"learning.":[66],"To":[67],"address":[68],"these":[69],"issues,":[70],"propose":[72],"a":[73,86,143],"modality-aware":[74],"contrastive":[75,139],"self-distillation":[79,144],"(MACIL-SD)":[80],"strategy":[81],".":[82],"Specifically,":[83],"leverage":[85],"lightweight":[87],"two-stream":[88],"network":[89],"generate":[91],"audio":[92,113],"visual":[94,115,151],"bags,":[95],"which":[97,157],"unimodal":[98,150,166],"background,":[99],"violent,":[100],"normal":[102,132],"are":[104,119,127,204],"clustered":[105],"into":[106],"semi-bags":[107,126],"unsupervised":[110],"way.":[111],"Then":[112],"violent":[116,125],"semi-bag":[117],"representations":[118],"assembled":[120],"as":[121,138,196],"positive":[122],"pairs,":[123],"combined":[128],"background":[130],"opposite":[136],"pairs.":[141],"Furthermore,":[142],"module":[145],"is":[146],"applied":[147],"transfer":[149],"knowledge":[152],"model,":[156],"alleviates":[158],"noises":[159],"closes":[161],"semantic":[163],"gap":[164],"between":[165],"features.":[169],"Experiments":[170],"show":[171],"that":[172,189],"our":[173,190],"framework":[174],"outperforms":[175],"previous":[176],"methods":[177],"lower":[179],"complexity":[180],"large-scale":[183],"XD-Violence":[184],"dataset.":[185],"Results":[186],"also":[187],"demonstrate":[188],"proposed":[191],"approach":[192],"can":[193],"be":[194],"used":[195],"plug-in":[197],"modules":[198],"enhance":[200],"other":[201],"networks.":[202],"Codes":[203],"available":[205],"at":[206],"https://github.com/JustinYuu/MACIL_SD.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}