{"id":"https://openalex.org/W4318751378","doi":"https://doi.org/10.48550/arxiv.2301.12048","title":"Making Reconstruction-based Method Great Again for Video Anomaly Detection","display_name":"Making Reconstruction-based Method Great Again for Video Anomaly Detection","publication_year":2023,"publication_date":"2023-01-28","ids":{"openalex":"https://openalex.org/W4318751378","doi":"https://doi.org/10.48550/arxiv.2301.12048"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.12048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.12048","pdf_url":"https://arxiv.org/pdf/2301.12048","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.12048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115580422","display_name":"Yizhou Wang","orcid":"https://orcid.org/0000-0003-1601-9649"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yizhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021042598","display_name":"Can Qin","orcid":"https://orcid.org/0000-0003-0712-5378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Can","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102281154","display_name":"Yue Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419183","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-5768-8235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031836304","display_name":"Xu Ma","orcid":"https://orcid.org/0000-0003-2012-9808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005819096","display_name":"Yun Fu","orcid":"https://orcid.org/0000-0002-5098-2853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115580422"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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":1.0,"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":0.984000027179718,"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/T12391","display_name":"Artificial Immune Systems Applications","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6847912073135376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6744388341903687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6469705104827881},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6423956751823425},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.5070247650146484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4649551808834076},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45529723167419434},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4481007754802704},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42121654748916626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32851681113243103},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1980767548084259}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6847912073135376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6744388341903687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469705104827881},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6423956751823425},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.5070247650146484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4649551808834076},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45529723167419434},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4481007754802704},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42121654748916626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32851681113243103},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1980767548084259}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.12048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.12048","pdf_url":"https://arxiv.org/pdf/2301.12048","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.12048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.12048","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.12048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.12048","pdf_url":"https://arxiv.org/pdf/2301.12048","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320337807","display_name":"U.S. Army Combat Capabilities Development Command","ror":null},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318751378.pdf","grobid_xml":"https://content.openalex.org/works/W4318751378.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W3099765033","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Anomaly":[0],"detection":[1,215,233],"in":[2,171],"videos":[3],"is":[4,96,193,238],"a":[5,85,99,116,226],"significant":[6],"yet":[7],"challenging":[8],"problem.":[9],"Previous":[10],"approaches":[11],"based":[12,195],"on":[13,29,196,211],"deep":[14],"neural":[15],"networks":[16],"employ":[17],"either":[18],"reconstruction-based":[19,25,118,223],"or":[20],"prediction-based":[21],"approaches.":[22],"Nevertheless,":[23],"existing":[24],"methods":[26,224],"1)":[27],"rely":[28],"old-fashioned":[30],"convolutional":[31,103],"autoencoders":[32],"and":[33,55,72,110,168,183,202,229],"are":[34,41],"poor":[35],"at":[36,240],"modeling":[37],"temporal":[38,108],"dependency;":[39],"2)":[40],"prone":[42],"to":[43,49,124,152,160],"overfit":[44],"the":[45,59,130,134,139,147,154,161,165,169,172,180,184,190,197,200],"training":[46],"samples,":[47],"leading":[48],"indistinguishable":[50],"reconstruction":[51,136,177,204],"errors":[52,205],"of":[53,138,146,157,164,199],"normal":[54,140],"abnormal":[56,148],"frames":[57,141],"during":[58,122],"inference":[60],"phase.":[61],"To":[62],"address":[63],"such":[64],"issues,":[65],"firstly,":[66],"we":[67,113,174],"get":[68],"inspiration":[69],"from":[70],"transformer":[71],"propose":[73],"${\\textbf":[74,77],"S}$patio-${\\textbf":[75],"T}$emporal":[76],"A}$uto-${\\textbf":[78],"T}$rans-${\\textbf":[79],"E}$ncoder,":[80],"dubbed":[81],"as":[82,84],"$\\textbf{STATE}$,":[83],"new":[86],"autoencoder":[87],"model":[88],"for":[89,106],"enhanced":[90],"consecutive":[91],"frame":[92,166,182],"reconstruction.":[93,158],"Our":[94],"STATE":[95],"equipped":[97],"with":[98],"specifically":[100],"designed":[101,194],"learnable":[102],"attention":[104],"module":[105],"efficient":[107],"learning":[109],"reasoning.":[111],"Secondly,":[112],"put":[114],"forward":[115],"novel":[117],"input":[119],"perturbation":[120,132],"technique":[121],"testing":[123,135],"further":[125],"differentiate":[126],"anomalous":[127],"frames.":[128],"With":[129],"same":[131],"magnitude,":[133],"error":[137],"lowers":[142],"more":[143],"than":[144],"that":[145,218],"frames,":[149],"which":[150],"contributes":[151],"mitigating":[153],"overfitting":[155],"problem":[156],"Owing":[159],"high":[162],"relevance":[163],"abnormality":[167],"objects":[170],"frame,":[173],"conduct":[175],"object-level":[176],"using":[178,206],"both":[179],"raw":[181,201],"corresponding":[185],"optical":[186],"flow":[187],"patches.":[188],"Finally,":[189],"anomaly":[191,214,232],"score":[192],"combination":[198],"motion":[203],"perturbed":[207],"inputs.":[208],"Extensive":[209],"experiments":[210],"benchmark":[212],"video":[213],"datasets":[216],"demonstrate":[217],"our":[219],"approach":[220],"outperforms":[221],"previous":[222],"by":[225],"notable":[227],"margin,":[228],"achieves":[230],"state-of-the-art":[231],"performance":[234],"consistently.":[235],"The":[236],"code":[237],"available":[239],"https://github.com/wyzjack/MRMGA4VAD.":[241]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-02-02T00:00:00"}