{"id":"https://openalex.org/W4402981165","doi":"https://doi.org/10.1109/icme57554.2024.10688202","title":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","display_name":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981165","doi":"https://doi.org/10.1109/icme57554.2024.10688202"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101560169","display_name":"Shengyang Sun","orcid":"https://orcid.org/0000-0003-3286-0585"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengyang Sun","raw_affiliation_strings":["College of Information Science & Electronic Engineering Zhejiang University,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science & Electronic Engineering Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061298101","display_name":"Xiaojin Gong","orcid":"https://orcid.org/0000-0001-9955-3569"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojin Gong","raw_affiliation_strings":["College of Information Science & Electronic Engineering Zhejiang University,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science & Electronic Engineering Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101560169"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.453,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90254125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9883000254631042,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9883000254631042,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9783999919891357,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bottleneck","display_name":"Bottleneck","score":0.6797646284103394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5995759963989258},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4712693393230438},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4303322732448578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4053478240966797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36404842138290405},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.20379865169525146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18149176239967346},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12994521856307983},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08550509810447693},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06801044940948486},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05976346135139465}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6797646284103394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5995759963989258},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4712693393230438},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4303322732448578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4053478240966797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36404842138290405},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.20379865169525146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18149176239967346},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12994521856307983},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08550509810447693},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06801044940948486},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05976346135139465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W3089682612","https://openalex.org/W4210416950","https://openalex.org/W4223499953","https://openalex.org/W4225280406","https://openalex.org/W4283827116","https://openalex.org/W4285206108","https://openalex.org/W4304098292","https://openalex.org/W4312384316","https://openalex.org/W4312658081","https://openalex.org/W4385245566","https://openalex.org/W4386065503","https://openalex.org/W4386076149","https://openalex.org/W4386160073","https://openalex.org/W6797528369","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1,59],"multimodal":[2,34],"violence":[3,9,35],"detection":[4,10,36],"aims":[5],"to":[6,86,103,117],"learn":[7],"a":[8,56,70,80,98,112],"model":[11],"by":[12],"leveraging":[13],"multiple":[14],"modalities":[15,95],"such":[16],"as":[17,47],"RGB,":[18],"optical":[19],"flow,":[20],"and":[21,42,90,96],"audio,":[22],"while":[23],"only":[24],"video-level":[25],"annotations":[26],"are":[27,45],"available.":[28],"In":[29,51],"the":[30,125,131],"pursuit":[31],"of":[32,83,94],"effective":[33],"(MVD),":[37],"information":[38,89],"redundancy,":[39],"modality":[40,43],"imbalance,":[41],"asynchrony":[44],"identified":[46],"three":[48],"key":[49],"challenges.":[50,66],"this":[52],"work,":[53],"we":[54,68,110],"propose":[55,111],"new":[57],"weakly":[58],"MVD":[60],"method":[61,133],"that":[62,78,130],"explicitly":[63],"addresses":[64],"these":[65],"Specifically,":[67],"introduce":[69],"multi-scale":[71],"bottleneck":[72,84,99],"transformer":[73],"(MSBT)":[74],"based":[75],"fusion":[76],"module":[77],"employs":[79],"reduced":[81],"number":[82],"tokens":[85],"gradually":[87],"condense":[88],"fuse":[91],"each":[92],"pair":[93],"utilizes":[97],"token-based":[100],"weighting":[101],"scheme":[102],"highlight":[104],"more":[105],"important":[106],"fused":[107,121],"features.":[108,122],"Furthermore,":[109],"temporal":[113],"consistency":[114],"contrast":[115],"loss":[116],"semantically":[118],"align":[119],"pairwise":[120],"Experiments":[123],"on":[124],"largest-scale":[126],"XD-Violence":[127],"dataset":[128],"demonstrate":[129],"proposed":[132],"achieves":[134],"state-of-the-art":[135],"performance.":[136],"Code":[137],"is":[138],"available":[139],"at":[140],"https://github.com/shengyangsun/MSBT.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}