{"id":"https://openalex.org/W7135169248","doi":"https://doi.org/10.1145/3801156","title":"SOR-BDNet: Semantic-Optical Representation for Boundary-Aware Video Anomaly Detection with GPT-4o","display_name":"SOR-BDNet: Semantic-Optical Representation for Boundary-Aware Video Anomaly Detection with GPT-4o","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135169248","doi":"https://doi.org/10.1145/3801156"},"language":"en","primary_location":{"id":"doi:10.1145/3801156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3801156","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.ulster.ac.uk/en/publications/eef6755f-c289-4521-a3ec-f9f8312a71b4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129087103","display_name":"Yi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]},{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland and Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-3981-4496","affiliations":[{"raw_affiliation_string":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland and Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I138801177","https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129020432","display_name":"Bryan W. Scotney","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]},{"id":"https://openalex.org/I2800980681","display_name":"Ulster Hospital","ror":"https://ror.org/04pmdg365","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2800980681","https://openalex.org/I4210166072"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bryan W. Scotney","raw_affiliation_strings":["Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-8243-2223","affiliations":[{"raw_affiliation_string":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I2800980681","https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiushan Nie","orcid":"https://orcid.org/0000-0001-9644-9723"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiushan Nie","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-9644-9723","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingbo Liu","orcid":"https://orcid.org/0000-0002-7236-8715"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingbo Liu","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-7236-8715","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0002-4821-6404"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]},{"id":"https://openalex.org/I2800980681","display_name":"Ulster Hospital","ror":"https://ror.org/04pmdg365","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2800980681","https://openalex.org/I4210166072"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-4821-6404","affiliations":[{"raw_affiliation_string":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I2800980681","https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123759516","display_name":"Lanting Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanting Qiu","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-4874-7176","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25313256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.984000027179718,"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":0.984000027179718,"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":0.0038999998942017555,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0008999999845400453,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6438999772071838},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5471000075340271},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5443000197410583},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4041000008583069},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.38999998569488525},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.895799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6438999772071838},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49140000343322754},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2680000066757202}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3801156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3801156","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/eef6755f-c289-4521-a3ec-f9f8312a71b4","is_oa":true,"landing_page_url":"https://pure.ulster.ac.uk/en/publications/eef6755f-c289-4521-a3ec-f9f8312a71b4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402454","display_name":"Ulster University Research Portal (Ulster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138801177","host_organization_name":"University of Ulster","host_organization_lineage":["https://openalex.org/I138801177"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sun, Y, W. Scotney, B, Nie, X, Liu, X, Zhang, S & Qiu, L 2026, 'SOR-BDNet: Semantic-Optical Representation for Boundary-Aware Video Anomaly Detection with GPT-4o', ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 22, no. 5, 126, pp. 1-23. https://doi.org/10.1145/3801156","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/eef6755f-c289-4521-a3ec-f9f8312a71b4","is_oa":true,"landing_page_url":"https://pure.ulster.ac.uk/en/publications/eef6755f-c289-4521-a3ec-f9f8312a71b4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402454","display_name":"Ulster University Research Portal (Ulster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138801177","host_organization_name":"University of Ulster","host_organization_lineage":["https://openalex.org/I138801177"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sun, Y, W. Scotney, B, Nie, X, Liu, X, Zhang, S & Qiu, L 2026, 'SOR-BDNet: Semantic-Optical Representation for Boundary-Aware Video Anomaly Detection with GPT-4o', ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 22, no. 5, 126, pp. 1-23. https://doi.org/10.1145/3801156","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7335766553878784,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2163612318","https://openalex.org/W2548197316","https://openalex.org/W2606538621","https://openalex.org/W2915683453","https://openalex.org/W2921491036","https://openalex.org/W2921906393","https://openalex.org/W2963610939","https://openalex.org/W2963795951","https://openalex.org/W2987146532","https://openalex.org/W2996443765","https://openalex.org/W3015832418","https://openalex.org/W3134566480","https://openalex.org/W3138648827","https://openalex.org/W3145726664","https://openalex.org/W3168600998","https://openalex.org/W3202590754","https://openalex.org/W4210391670","https://openalex.org/W4220869155","https://openalex.org/W4281478450","https://openalex.org/W4379648877","https://openalex.org/W4386071599","https://openalex.org/W4387350587","https://openalex.org/W4389104972","https://openalex.org/W4402727764","https://openalex.org/W4402753378","https://openalex.org/W4402754070","https://openalex.org/W4402775263","https://openalex.org/W4408960433","https://openalex.org/W4410027467"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Video":[3],"Anomaly":[4],"Detection":[5,56],"(VAD)":[6],"has":[7],"shifted":[8],"from":[9,32,129,134],"conventional":[10],"appearance-based":[11],"modeling":[12],"to":[13,71,84,98],"semantically":[14,40],"driven":[15],"frameworks":[16],"empowered":[17],"by":[18,125],"LLMs.":[19],"Traditional":[20],"reconstruction-":[21],"and":[22,68,89,119,171,182,190,200,210],"prediction-based":[23],"methods,":[24],"relying":[25],"on":[26,158,165],"motion":[27,69,87,120],"or":[28],"appearance":[29,67],"patterns":[30],"learned":[31],"normal":[33,41,135],"data,":[34],"often":[35],"misclassify":[36],"previously":[37],"unseen":[38],"yet":[39],"events":[42],"as":[43],"anomalies.":[44],"To":[45,137],"address":[46],"this":[47],"limitation,":[48],"we":[49,81,142],"propose":[50],"SOR-BDNet":[51,174],"(Semantic-Optical":[52],"Representation":[53],"with":[54,95,153],"Boundary":[55],"Network),":[57],"an":[58],"annotation-free":[59],"multimodal":[60],"VAD":[61],"framework":[62],"that":[63,112,148,173],"jointly":[64],"leverages":[65],"visual":[66,150],"dynamics":[70],"generate":[72],"interpretable":[73],"semantic":[74,114,127],"representations":[75,105],"at":[76,215],"the":[77,91,188,193],"frame":[78],"level.":[79],"Specifically,":[80],"employ":[82],"RAFT":[83],"estimate":[85],"dense":[86],"fields":[88],"concatenate":[90],"resulting":[92],"flow":[93],"maps":[94],"RGB":[96],"images":[97],"form":[99],"unified":[100],"spatiotemporal":[101],"inputs.":[102],"These":[103,185],"fused":[104],"are":[106,123,213],"fed":[107],"into":[108],"a":[109,130,144,159],"GPT-4o-based":[110],"module":[111,147],"generates":[113],"captions":[115],"capturing":[116],"object":[117],"semantics":[118],"cues.":[121],"Anomalies":[122],"detected":[124],"measuring":[126],"deviations":[128],"memory":[131],"bank":[132],"constructed":[133],"captions.":[136],"further":[138],"refine":[139],"temporal":[140],"boundaries,":[141],"design":[143],"boundary":[145],"refinement":[146],"integrates":[149],"continuity":[151],"constraints":[152],"contrastive":[154],"feature":[155],"learning":[156],"based":[157],"Swin":[160],"Transformer":[161],"backbone.":[162],"Extensive":[163],"experiments":[164],"four":[166],"challenging":[167],"benchmarks\u2014UCSD-Ped2,":[168],"Avenue,":[169],"ShanghaiTech,":[170],"UCF-Crime\u2014demonstrate":[172],"achieves":[175],"frame-level":[176],"accuracies":[177],"of":[178,192],"97.96%,":[179],"82.86%,":[180],"87.36%,":[181],"85.64%,":[183],"respectively.":[184],"results":[186],"highlight":[187],"robustness":[189],"scalability":[191],"proposed":[194],"framework,":[195],"while":[196],"significantly":[197],"improving":[198],"interpretability":[199],"generalization":[201],"across":[202],"diverse":[203],"real-world":[204],"surveillance":[205],"scenarios.":[206],"The":[207],"source":[208],"code":[209],"pretrained":[211],"models":[212],"available":[214],"https://github.com/syi-coder/SOR-BDNet-Semantic-Optical-Representation-for-Boundary-Aware-Video-Anomaly-Detection-with-GPT-4o":[216],".":[217]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-14T00:00:00"}