{"id":"https://openalex.org/W4406258402","doi":"https://doi.org/10.1109/ojcs.2024.3517154","title":"Multimodal Attention-Enhanced Feature Fusion-Based Weakly Supervised Anomaly Violence Detection","display_name":"Multimodal Attention-Enhanced Feature Fusion-Based Weakly Supervised Anomaly Violence Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406258402","doi":"https://doi.org/10.1109/ojcs.2024.3517154"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2024.3517154","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3517154","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2024.3517154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005221038","display_name":"Jungpil Shin","orcid":"https://orcid.org/0000-0002-7476-2468"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jungpil Shin","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017981507","display_name":"Abu Saleh Musa Miah","orcid":"https://orcid.org/0000-0002-1238-0464"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Abu Saleh Musa Miah","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103068034","display_name":"Yuta Kaneko","orcid":"https://orcid.org/0009-0003-8087-7602"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Kaneko","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947983","display_name":"Najmul Hassan","orcid":"https://orcid.org/0009-0000-6499-1825"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Najmul Hassan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006048610","display_name":"Hyoun-Sup Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I204974687","display_name":"Dong-Eui University","ror":"https://ror.org/059g69b28","country_code":"KR","type":"education","lineage":["https://openalex.org/I204974687"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoun-Sup Lee","raw_affiliation_strings":["Department of Game Engineering, Dongeui University, Busan, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Game Engineering, Dongeui University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I204974687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043467630","display_name":"Si-Woong Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I204974687","display_name":"Dong-Eui University","ror":"https://ror.org/059g69b28","country_code":"KR","type":"education","lineage":["https://openalex.org/I204974687"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Si-Woong Jang","raw_affiliation_strings":["Department of Computer Engineering, Dongeui University, Busan, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Dongeui University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I204974687"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005221038"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":16.8457,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98686493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"129","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.991599977016449,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9750000238418579,"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":0.8455619812011719},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6876293420791626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386948823928833},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6006823182106018},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5804219245910645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5545769333839417},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5043741464614868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48914578557014465},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4779401123523712},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32859066128730774},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10484558343887329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455619812011719},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6876293420791626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386948823928833},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6006823182106018},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5804219245910645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5545769333839417},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5043741464614868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48914578557014465},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4779401123523712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32859066128730774},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10484558343887329},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2024.3517154","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3517154","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9cd72458f63943398da91c1f4345b862","is_oa":true,"landing_page_url":"https://doaj.org/article/9cd72458f63943398da91c1f4345b862","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 6, Pp 129-140 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2024.3517154","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3517154","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327819","display_name":"Ministry of SMEs and Startups","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1578985305","https://openalex.org/W1983364832","https://openalex.org/W2122646361","https://openalex.org/W2921491036","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2970271202","https://openalex.org/W2982190919","https://openalex.org/W3035021504","https://openalex.org/W3035699237","https://openalex.org/W3089682612","https://openalex.org/W3093041714","https://openalex.org/W3101133846","https://openalex.org/W3119259789","https://openalex.org/W3136793533","https://openalex.org/W3202896130","https://openalex.org/W4206784731","https://openalex.org/W4210416950","https://openalex.org/W4213288912","https://openalex.org/W4223913677","https://openalex.org/W4225280406","https://openalex.org/W4247755631","https://openalex.org/W4283827116","https://openalex.org/W4293518932","https://openalex.org/W4293519347","https://openalex.org/W4304098292","https://openalex.org/W4312889062","https://openalex.org/W4313503779","https://openalex.org/W4313855621","https://openalex.org/W4317528903","https://openalex.org/W4317537389","https://openalex.org/W4319299969","https://openalex.org/W4322503366","https://openalex.org/W4360614118","https://openalex.org/W4382202314","https://openalex.org/W4382464562","https://openalex.org/W4386076087","https://openalex.org/W4386076149","https://openalex.org/W4386160073","https://openalex.org/W4386496618","https://openalex.org/W4386597062","https://openalex.org/W4388901869","https://openalex.org/W4389776582","https://openalex.org/W4390703358","https://openalex.org/W4390944852","https://openalex.org/W4391097000","https://openalex.org/W4391614403","https://openalex.org/W4392251920","https://openalex.org/W4392454692","https://openalex.org/W4393935562","https://openalex.org/W4396506363","https://openalex.org/W4396877929","https://openalex.org/W4401226124","https://openalex.org/W4401568477","https://openalex.org/W4401935126","https://openalex.org/W4402265131","https://openalex.org/W4402981165","https://openalex.org/W4403022323","https://openalex.org/W6637373629","https://openalex.org/W6757107679","https://openalex.org/W6766008006","https://openalex.org/W6791353385","https://openalex.org/W6856015427"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W2023355163","https://openalex.org/W4386083130","https://openalex.org/W3154990682","https://openalex.org/W3111737715","https://openalex.org/W2560201613","https://openalex.org/W2069571255","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W2163164795"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"video":[2,117],"anomaly":[3,246],"detection":[4,110,247],"(WS-VAD)":[5],"plays":[6],"a":[7,64,121,137,183,200],"pivotal":[8],"role":[9],"in":[10,212,306],"advancing":[11],"intelligent":[12],"surveillance":[13],"systems":[14],"within":[15],"the":[16,48,109,115,142,166,178,207,221,262,277,283,289],"field":[17],"of":[18,169,186,229,259,274,291],"computer":[19],"vision.":[20],"Despite":[21],"significant":[22],"research,":[23],"WS-VAD":[24,52,66,307],"continues":[25],"to":[26,35,77,107,127],"face":[27],"challenges,":[28],"particularly":[29],"with":[30,71,136,148,220],"unimodal":[31],"approaches":[32],"that":[33],"struggle":[34],"extract":[36],"meaningful":[37],"features":[38,101,145,195],"effectively.":[39],"A":[40],"few":[41],"research":[42],"studies":[43],"have":[44],"been":[45],"done":[46],"on":[47,261,276,282],"multimodal":[49,69,252],"dataset":[50,279],"fusion-based":[51],"system,":[53],"and":[54,91,99,112,130,150,171,203,235,249,271,280,302],"their":[55],"performance":[56],"accuracy":[57,111,248],"is":[58],"unsatisfactory.":[59],"In":[60,114],"response,":[61],"we":[62,119],"propose":[63],"novel":[65],"system":[67,82],"leveraging":[68],"datasets":[70,301],"an":[72,103,216,255],"attention-enhanced":[73],"feature":[74,124],"fusion":[75,228,253],"approach":[76],"address":[78],"these":[79,230],"challenges.":[80],"Our":[81,251],"integrates":[83],"three":[84,231,299],"distinct":[85],"data":[86,198],"modalities\u2014RGB":[87],"video,":[88],"optical":[89],"flow,":[90],"audio":[92,208,236],"signals\u2014where":[93],"each":[94],"stream":[95,191,209],"extracts":[96,192],"complementary":[97],"spatial":[98,129],"temporal":[100,131],"using":[102,199],"enhanced":[104,193],"attention":[105,204,217],"module":[106,218],"improve":[108],"robustness.":[113,250],"RGB":[116],"stream,":[118],"employ":[120],"multi-stage,":[122],"attention-driven":[123],"enhancement":[125],"process":[126,134],"refine":[128],"features.":[132,153],"This":[133],"begins":[135],"ViT-based":[138],"CLIP":[139],"module,":[140],"where":[141],"top":[143],"k":[144],"are":[146,156],"concatenated":[147],"I3D-":[149],"TCA-based":[151],"spatiotemporal":[152,194],"Temporal":[154],"dependencies":[155],"then":[157],"captured":[158],"through":[159,215],"uncertainty-regulated":[160],"dual":[161],"memory":[162],"units":[163],"(UR-DMUs),":[164],"allowing":[165],"simultaneous":[167],"learning":[168,202],"normal":[170],"anomalous":[172],"patterns.":[173],"The":[174,189,227],"final":[175],"stage":[176],"selects":[177],"most":[179],"relevant":[180],"features,":[181],"yielding":[182],"refined":[184],"representation":[185],"RGB-based":[187],"data.":[188],"second":[190],"from":[196],"flow":[197],"deep":[201],"module.":[205],"Lastly,":[206],"detects":[210],"anomalies":[211],"sound":[213],"patterns":[214],"integrated":[219],"VGGish":[222],"model,":[223],"capturing":[224],"auditory":[225],"cues.":[226],"streams":[232],"captures":[233],"motion":[234],"signals":[237],"often":[238],"missed":[239],"by":[240,268],"visual":[241],"analysis":[242],"alone,":[243],"significantly":[244],"enhancing":[245],"achieves":[254],"average":[256],"precision":[257],"(AP)":[258],"88.28%":[260],"XD-Violence":[263],"dataset,":[264],"outperforming":[265],"prior":[266],"models":[267],"nearly":[269],"2%,":[270],"attains":[272],"AUCs":[273],"98.71%":[275],"ShanghaiTech":[278],"90.26%":[281],"UCF-Crime":[284],"dataset.":[285],"These":[286],"results":[287],"underscore":[288],"effectiveness":[290],"our":[292],"approach,":[293],"consistently":[294],"surpassing":[295],"existing":[296],"methods":[297],"across":[298],"benchmark":[300],"validating":[303],"its":[304],"robustness":[305],"applications.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-01-11T00:00:00"}