{"id":"https://openalex.org/W4390479014","doi":"https://doi.org/10.1145/3595916.3626375","title":"A Cross-modal and Redundancy-reduced Network for Weakly-Supervised Audio-Visual Violence Detection","display_name":"A Cross-modal and Redundancy-reduced Network for Weakly-Supervised Audio-Visual Violence Detection","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479014","doi":"https://doi.org/10.1145/3595916.3626375"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626375","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","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/10.1145/3595916.3626375","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049439264","display_name":"Yidan Fan","orcid":"https://orcid.org/0009-0002-8106-9853"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yidan Fan","raw_affiliation_strings":["School of Future Technology &amp; College of Intelligence and Computing, Tianjin University, CN"],"affiliations":[{"raw_affiliation_string":"School of Future Technology &amp; College of Intelligence and Computing, Tianjin University, CN","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029368027","display_name":"Yongxin Yu","orcid":"https://orcid.org/0000-0002-2515-8061"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Yu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, CN"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, CN","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, CN"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, CN","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, CN"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, CN","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049439264"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19119129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9934999942779541,"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":0.7696365118026733},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7460190057754517},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6721459627151489},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5920798182487488},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.555457353591919},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5432333946228027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5370359420776367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4866712689399719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41995108127593994},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14562588930130005},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12746474146842957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696365118026733},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7460190057754517},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6721459627151489},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5920798182487488},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.555457353591919},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5432333946228027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5370359420776367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4866712689399719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41995108127593994},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14562588930130005},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12746474146842957},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626375","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626375","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G1100817172","display_name":null,"funder_award_id":"619320","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1297212625","display_name":null,"funder_award_id":"62376186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1829462488","display_name":null,"funder_award_id":"61932009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7537086629","display_name":null,"funder_award_id":"6193200","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479014.pdf","grobid_xml":"https://content.openalex.org/works/W4390479014.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W3035333188","https://openalex.org/W3134566480","https://openalex.org/W3136793533","https://openalex.org/W3153639479","https://openalex.org/W3167008019","https://openalex.org/W4226143692","https://openalex.org/W4304098292","https://openalex.org/W4311037942","https://openalex.org/W4311408427","https://openalex.org/W4312753781"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2185469136","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2011264131","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1],"using":[2],"audio":[3,34,68],"and":[4,21,35,47,93],"visual":[5,36,64],"information":[6,41],"has":[7],"improved":[8],"Violence":[9,99],"Detection":[10],"tasks.":[11],"However,":[12],"previous":[13,150],"studies":[14],"overlook":[15],"the":[16,22,30,44,52,62,144],"gap":[17],"between":[18,33,116],"pre-trained":[19],"networks":[20],"final":[23],"violence":[24,83,156],"detection":[25,59],"task,":[26],"as":[27,29,54,70],"well":[28],"semantic":[31,48],"inconsistency":[32],"features.":[37],"We":[38,75],"consider":[39],"task-irrelevant":[40],"caused":[42],"by":[43],"former":[45],"situation":[46],"noise":[49],"due":[50],"to":[51,113,125],"latter":[53],"redundancy,":[55],"negatively":[56],"affecting":[57],"overall":[58],"performance.":[60],"Besides,":[61],"prevailing":[63],"modality-centric":[65],"approach":[66],"with":[67,107,152],"features":[69],"guidance":[71],"may":[72],"be":[73],"biased.":[74],"contend":[76],"that":[77],"both":[78,139],"modalities":[79],"are":[80],"crucial":[81],"in":[82,155],"detection.":[84,157],"To":[85],"address":[86],"these":[87],"issues,":[88],"we":[89,119],"propose":[90],"a":[91,104,108,121,129],"Cross-modal":[92],"Redundancy-reduced":[94],"Network":[95],"for":[96,135],"Weakly-Supervised":[97],"Audio-Visual":[98],"Detection.":[100],"Our":[101],"framework":[102],"integrates":[103],"relation-ware":[105],"module":[106,132],"bi-directional":[109],"cross-modal":[110],"attention":[111],"mechanism":[112],"explore":[114],"interactions":[115],"modalities.":[117,140],"Then,":[118],"introduce":[120],"feature":[122],"filter":[123],"gate":[124],"reduce":[126],"redundancy.":[127],"Finally,":[128],"multi-branch":[130],"classification":[131],"is":[133],"proposed":[134],"better":[136],"utilization":[137],"of":[138,146],"Extensive":[141],"experiments":[142],"demonstrate":[143],"effectiveness":[145],"our":[147],"approach,":[148],"surpassing":[149],"methods":[151],"state-of-the-art":[153],"performance":[154]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
