Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly Detection

Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly Detection | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly Detection Wei Liu, cong wang, yongkang Zhang, Jun Chen, longsheng wei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4521096/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Video anomaly detection is a challenging problem characterized by significant uncertainty, as it is influenced by various factors including appearance, posture, light intensity, scene changes, and etc. To alleviate the influence of the above factors, this article focuses more on the description of skeleton features. We use the Normalizing Flow framework to process human pose data to reduce the impact of strong generalization capabilities of other models. However, Normalizing Flow algorithms were unable to fully utilize the dependencies between non-directly connected nodes when convolving posture data, and ignored the spatial differences of nodes in the human body structure. Hence, we propose an improved video anomaly detection model called Adaptive Graph Convolution Normalizing Flow(AGC-NF). Our model can generate relationships between nodes that are not directly connected, and can adaptively update the connection relationship and connection strength between each node through training. Simultaneously, the incorporation of spatial distance constraints into node division amplifies local distinctions. After experimental evaluation, AGC-NF achieves improvement over mainstream Normalizing Flow methods on ShanghaiTech-HR datasets and UBnormal datasets. Video Anomaly Detection Human Pose Normalizing Flow Adaptive Graph Convolutional Network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4521096","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":313645196,"identity":"0482e0b6-d6fd-4929-8894-bed94e52be13","order_by":0,"name":"Wei Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuElEQVRIiWNgGAWjYBACPmYQaWAD4fEQo4UNoiWNFC0Q6jApWth5zCQ+FJyXNzi/gPHB2zYGeXPCDuMxk5xhcNtww40HzIZz2xgMdzYQoeU2j8HtBIMbB9ikedsYEgwOEKPlj8E5kBb238RrYTA4kGBwvoGNmUgtbOU/ewySDWfeYGyWnHNOwnADIS38/Ic3G/z4YyfPd/7wwQ9vymzkCdqCABKJDSCSaPUg+4g3fRSMglEwCkYYAACg6DjT8Nh4JwAAAABJRU5ErkJggg==","orcid":"","institution":"China University of Geosciences,wuhan","correspondingAuthor":true,"prefix":"","firstName":"Wei","middleName":"","lastName":"Liu","suffix":""},{"id":313645197,"identity":"5a5d2ba1-5df8-4caf-b7cb-8f3fd0c927de","order_by":1,"name":"cong wang","email":"","orcid":"","institution":"China University of Geosciences,wuhan","correspondingAuthor":false,"prefix":"","firstName":"cong","middleName":"","lastName":"wang","suffix":""},{"id":313645198,"identity":"ca63c0fd-2802-4acd-8c38-ecd98ecefa4f","order_by":2,"name":"yongkang Zhang","email":"","orcid":"","institution":"China University of Geosciences,wuhan","correspondingAuthor":false,"prefix":"","firstName":"yongkang","middleName":"","lastName":"Zhang","suffix":""},{"id":313645199,"identity":"23c5bbc8-b491-4d89-93f1-82fd0b418836","order_by":3,"name":"Jun Chen","email":"","orcid":"","institution":"China University of Geosciences,wuhan","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Chen","suffix":""},{"id":313645200,"identity":"de219b1d-6f89-4d95-8f40-c65216281448","order_by":4,"name":"longsheng wei","email":"","orcid":"","institution":"China University of Geosciences,wuhan","correspondingAuthor":false,"prefix":"","firstName":"longsheng","middleName":"","lastName":"wei","suffix":""}],"badges":[],"createdAt":"2024-06-03 10:14:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4521096/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4521096/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91290837,"identity":"d6b3b4bd-4b05-4dd6-b204-b9f52c291630","added_by":"auto","created_at":"2025-09-15 00:46:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4959653,"visible":true,"origin":"","legend":"","description":"","filename":"AGCNF2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4521096/v1_covered_b96be1ed-4e1b-4d24-b698-5c92eb00de6b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Video Anomaly Detection , Human Pose , Normalizing Flow , Adaptive Graph Convolutional Network","lastPublishedDoi":"10.21203/rs.3.rs-4521096/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4521096/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Video anomaly detection is a challenging problem characterized by significant uncertainty, as it is influenced by various factors including appearance, posture, light intensity, scene changes, and etc. To alleviate the influence of the above factors, this article focuses more on the description of skeleton features. We use the Normalizing Flow framework to process human pose data to reduce the impact of strong generalization capabilities of other models. However, Normalizing Flow algorithms were unable to fully utilize the dependencies between non-directly connected nodes when convolving posture data, and ignored the spatial differences of nodes in the human body structure. Hence, we propose an improved video anomaly detection model called Adaptive Graph Convolution Normalizing Flow(AGC-NF). Our model can generate relationships between nodes that are not directly connected, and can adaptively update the connection relationship and connection strength between each node through training. Simultaneously, the incorporation of spatial distance constraints into node division amplifies local distinctions. After experimental evaluation, AGC-NF achieves improvement over mainstream Normalizing Flow methods on ShanghaiTech-HR datasets and UBnormal datasets. ","manuscriptTitle":"Adaptive Graph Convolution Embedding Normalizing Flow for Video Anomaly Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-18 04:02:48","doi":"10.21203/rs.3.rs-4521096/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bf4aa11b-f5bd-4f3d-9dde-07133c873160","owner":[],"postedDate":"June 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-15T00:38:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-18 04:02:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4521096","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4521096","identity":"rs-4521096","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}