{"id":"https://openalex.org/W4403780794","doi":"https://doi.org/10.1145/3664647.3681442","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","display_name":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780794","doi":"https://doi.org/10.1145/3664647.3681442"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681442","doi":"https://doi.org/10.1145/3664647.3681442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681442","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.05905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032693575","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0003-2938-6798","observed_orcids":["https://orcid.org/0000-0003-2938-6798"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-2938-6798","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112285634","display_name":"Xuerong Zhou","orcid":"https://orcid.org/0009-0007-0460-6009","observed_orcids":["https://orcid.org/0009-0007-0460-6009"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuerong Zhou","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0007-0460-6009","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039104219","display_name":"Guansong Pang","orcid":"https://orcid.org/0000-0002-9877-2716","observed_orcids":["https://orcid.org/0000-0002-9877-2716"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guansong Pang","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9877-2716","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008972548","display_name":"Zhiwei Yang","orcid":"https://orcid.org/0000-0001-9896-4518","observed_orcids":["https://orcid.org/0000-0001-9896-4518","https://orcid.org/0009-0001-6160-2924"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Yang","raw_affiliation_strings":["Xidian University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9896-4518","affiliations":[{"raw_affiliation_string":"Xidian University, Guangzhou, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081607584","display_name":"Qingsen Yan","orcid":"https://orcid.org/0000-0003-1010-3540","observed_orcids":["https://orcid.org/0000-0003-1010-3540"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingsen Yan","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-1010-3540","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010733532","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0001-7689-3405","observed_orcids":["https://orcid.org/0000-0001-7689-3405"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7689-3405","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057","observed_orcids":["https://orcid.org/0000-0002-2977-8057","https://orcid.org/0009-0001-7388-763X"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-2977-8057","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4327,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.99256331,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9301","last_page":"9310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9932000041007996,"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":0.9932000041007996,"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":0.002099999925121665,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0008999999845400453,"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/weakly-supervised-video-anomaly-detection","display_name":"weakly supervised video anomaly detection","score":0.9909999966621399},{"id":"https://openalex.org/keywords/anomaly-localization","display_name":"anomaly localization","score":0.8370000123977661},{"id":"https://openalex.org/keywords/prompt-embeddings","display_name":"prompt embeddings","score":0.9549999833106995},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.984000027179718},{"id":"https://openalex.org/keywords/two-stream-network","display_name":"two-stream network","score":0.9100000262260437},{"id":"https://openalex.org/keywords/motion-priors","display_name":"motion priors","score":0.7170000076293945},{"id":"https://openalex.org/keywords/background-interference","display_name":"background interference","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.763205349445343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756243705749512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5658817291259766},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.42012184858322144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40752658247947693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3790418803691864},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05616721510887146},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3664647.3681442","doi":"https://doi.org/10.1145/3664647.3681442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681442","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.05905","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05905","pdf_url":"https://arxiv.org/pdf/2408.05905","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10758","doi":null,"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9758","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3664647.3681442","raw_type":"Conference Proceeding Article"},{"id":"doi:10.48550/arxiv.2408.05905","doi":"https://doi.org/10.48550/arxiv.2408.05905","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.05905","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.05905","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.05905","pdf_url":"https://arxiv.org/pdf/2408.05905","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2694913583","display_name":null,"funder_award_id":"D5000220431","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6711904613","display_name":null,"funder_award_id":"62301432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7235411402","display_name":null,"funder_award_id":"2023TQ0272","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7446798810","display_name":null,"funder_award_id":"62306240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8813799148","display_name":null,"funder_award_id":"U23B2013","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403780794.pdf","grobid_xml":"https://content.openalex.org/works/W4403780794.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1483870316","https://openalex.org/W1522734439","https://openalex.org/W1967456674","https://openalex.org/W2012931101","https://openalex.org/W2163612318","https://openalex.org/W2341058432","https://openalex.org/W2492794003","https://openalex.org/W2507009361","https://openalex.org/W2559655401","https://openalex.org/W2611596598","https://openalex.org/W2619082050","https://openalex.org/W2753526808","https://openalex.org/W2766042539","https://openalex.org/W2783882151","https://openalex.org/W2788945907","https://openalex.org/W2897879219","https://openalex.org/W2913338238","https://openalex.org/W2921491036","https://openalex.org/W2960737790","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963610939","https://openalex.org/W2963645879","https://openalex.org/W2972156365","https://openalex.org/W2981650061","https://openalex.org/W2982190919","https://openalex.org/W2982875523","https://openalex.org/W3012693338","https://openalex.org/W3014352273","https://openalex.org/W3037420336","https://openalex.org/W3081430643","https://openalex.org/W3082213779","https://openalex.org/W3089682612","https://openalex.org/W3092920241","https://openalex.org/W3094502228","https://openalex.org/W3104870221","https://openalex.org/W3136793533","https://openalex.org/W3168600998","https://openalex.org/W3173407577","https://openalex.org/W3175528717","https://openalex.org/W3184357402","https://openalex.org/W3186300274","https://openalex.org/W3191725983","https://openalex.org/W3198377975","https://openalex.org/W3200038569","https://openalex.org/W3200904534","https://openalex.org/W3212044949","https://openalex.org/W3212899624","https://openalex.org/W4210416950","https://openalex.org/W4283811196","https://openalex.org/W4304084053","https://openalex.org/W4304091545","https://openalex.org/W4312560592","https://openalex.org/W4313053147","https://openalex.org/W4313291134","https://openalex.org/W4320476215","https://openalex.org/W4382464562","https://openalex.org/W4383428585","https://openalex.org/W4386065385","https://openalex.org/W4386076087","https://openalex.org/W4386076578","https://openalex.org/W4386160073","https://openalex.org/W4386597062","https://openalex.org/W4387614569","https://openalex.org/W4387968140","https://openalex.org/W4388093086","https://openalex.org/W4393153999","https://openalex.org/W4402265131","https://openalex.org/W4402727956","https://openalex.org/W4402733578","https://openalex.org/W4402775275","https://openalex.org/W4404420613"],"related_works":["https://openalex.org/W7167717637","https://openalex.org/W7166723023","https://openalex.org/W7131812201","https://openalex.org/W4417302374","https://openalex.org/W7155032314","https://openalex.org/W4399268507","https://openalex.org/W4402265131","https://openalex.org/W7162028060","https://openalex.org/W4400233241","https://openalex.org/W4413353939"],"abstract_inverted_index":{"Current":[0],"weakly":[1,101],"supervised":[2,102],"video":[3,30,58,103,182],"anomaly":[4,104,183],"detection":[5,14,105,184],"(WSVAD)":[6],"task":[7],"aims":[8],"to":[9,36,48],"achieve":[10],"frame-level":[11,34,63],"anomalous":[12,45],"event":[13],"with":[15,123,163],"only":[16],"coarse":[17],"video-level":[18],"annotations":[19,197],"available.":[20],"Existing":[21],"works":[22,66],"typically":[23],"involve":[24],"extracting":[25],"global":[26],"features":[27],"from":[28,144,152],"full-resolution":[29],"frames":[31],"and":[32,75,106,131,147],"training":[33],"classifiers":[35],"detect":[37],"anomalies":[38],"in":[39,50],"the":[40,56,71,77,80,128,132,136,141,187,212],"temporal":[41,129],"dimension.":[42,138],"However,":[43],"most":[44],"events":[46],"tend":[47],"occur":[49],"localized":[51],"spatial":[52,137],"regions":[53,165,177],"rather":[54],"than":[55],"entire":[57],"frames,":[59],"which":[60],"implies":[61],"existing":[62],"feature":[64],"based":[65,109],"may":[67],"be":[68],"misled":[69],"by":[70],"dominant":[72],"background":[73,190],"information":[74],"lack":[76],"interpretation":[78],"of":[79,166,170,178,189],"detected":[81],"anomalies.":[82],"To":[83],"address":[84],"this":[85,87],"dilemma,":[86],"paper":[88],"introduces":[89],"a":[90,119],"novel":[91],"method":[92,117,203],"called":[93],"STPrompt":[94],"that":[95,160],"learns":[96,157],"spatio-temporal":[97,164,196],"prompt":[98,158],"embeddings":[99,159],"for":[100,173,211],"localization":[107],"(WSVADL)":[108],"on":[110,127,135,194,207],"pre-trained":[111,145],"vision-language":[112],"models":[113],"(VLMs).":[114],"Our":[115],"proposed":[116],"employs":[118],"two-stream":[120],"network":[121],"structure,":[122],"one":[124],"stream":[125],"focusing":[126],"dimension":[130],"other":[133],"primarily":[134],"By":[139],"leveraging":[140],"learned":[142],"knowledge":[143],"VLMs":[146],"incorporating":[148],"natural":[149],"motion":[150],"priors":[151],"raw":[153],"videos,":[154],"our":[155,202],"model":[156],"are":[161],"aligned":[162],"videos":[167],"(e.g.,":[168],"patches":[169],"individual":[171],"frames)":[172],"identify":[174],"specific":[175],"local":[176],"anomalies,":[179],"enabling":[180],"accurate":[181],"while":[185],"mitigating":[186],"influence":[188],"information.":[191],"Without":[192],"relying":[193],"detailed":[195],"or":[198],"auxiliary":[199],"object":[200],"detection/tracking,":[201],"achieves":[204],"state-of-the-art":[205],"performance":[206],"three":[208],"public":[209],"benchmarks":[210],"WSVADL":[213],"task.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":43},{"year":2025,"cited_by_count":17}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2024-10-26T00:00:00"}