MultiScale3D: A Multi-Scale Fusion Algorithm for Action Recognition

MultiScale3D: A Multi-Scale Fusion Algorithm for Action Recognition | 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 MultiScale3D: A Multi-Scale Fusion Algorithm for Action Recognition XueJun Liu, Zhaichao Tang, Yonghao Wu, Zikang Du, Xuerui Wang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6218997/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 Camera-based behavior recognition is an effective means to prevent accidents. However, when a single camera is used to identify distant and close-range people's behaviors in a complex background, it is difficult to extract global and local features with different resolutions simultaneously, resulting in low recognition accuracy and slow recognition speed. In this paper, a multi-scale fusion motion recognition method, MultiScale3D, is proposed. First of all, based on YOLO-Pose technology, we put forward the remote and near synchronous bone key point extraction module, which improves the collaborative extraction speed of remote and near motion features. Then, a three-level ResNet module is designed to realize feature sampling with different resolutions, and the features of each level are splicing with the features of the other two levels respectively to achieve multi-scale feature fusion. The multi-scale information is weighted by the proposed MultiScale3D module, which further enhances the expression ability of key features. Among the experimental results of three public datasets, the model achieved an accuracy of 94.4% (state of arts) on NTU60-Xsub and 95.9% on FineGYM dataset. At the same time, the algorithm shows good robustness and generalization in the recognition of distant and close-range behaviors. Training code are available at https://github.com/Zhai-Mao/MultiScale3D Multiscale3D Action recognition Skeleton Keypoint detection ResNet modules YOLO-Pose 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-6218997","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":442733285,"identity":"4a692f1d-3e5e-4e22-ba33-7a57c1423f92","order_by":0,"name":"XueJun Liu","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"XueJun","middleName":"","lastName":"Liu","suffix":""},{"id":442733286,"identity":"15c3215c-6560-45e3-a95a-fc5210d4c6c8","order_by":1,"name":"Zhaichao Tang","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhaichao","middleName":"","lastName":"Tang","suffix":""},{"id":442733287,"identity":"527459bc-8c43-4bce-a115-9ac046b6173a","order_by":2,"name":"Yonghao Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYPCCAwwM7D0gEsImUgvPGSCZQJIWiRwgTYwWgxs5ho8Lft2R55d8e/Bw4Q8GOb4bCYyfC/BrMTae2ffMcObsvITDMxIYjCVvJDBLz8CjxexGjpk0b89hxg23cwwO8yQwJG64kcDGzEOEFvsNN8+AtdQTp4Xnx2Gg4TxgLQkGhLTYn3lWbMzbcDh5Zg/IL2kShjPPPGyWxqdFsj1542OeP4dt+9nPHv5cYGMjz3c8+eBnfFoYGDgMGBjbIExmYOwAKcYGvBqACeUBA8MfuJZRMApGwSgYBZgAABp5U9p1F4UZAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":true,"prefix":"","firstName":"Yonghao","middleName":"","lastName":"Wu","suffix":""},{"id":442733288,"identity":"351d9d2c-f98d-421d-a56d-a1842c58f6b7","order_by":3,"name":"Zikang Du","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Zikang","middleName":"","lastName":"Du","suffix":""},{"id":442733289,"identity":"84061baa-4663-42bf-a676-464d2b38eee7","order_by":4,"name":"Xuerui Wang","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Xuerui","middleName":"","lastName":"Wang","suffix":""},{"id":442733290,"identity":"a3faecc2-64fd-49e0-bab6-eef796e89cf7","order_by":5,"name":"Ruixiang Zhai","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Ruixiang","middleName":"","lastName":"Zhai","suffix":""},{"id":442733291,"identity":"789c087d-f895-4bd7-bb16-52203e2fe9ff","order_by":6,"name":"Yong Yan","email":"","orcid":"","institution":"Beijing Institute of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2025-03-13 10:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6218997/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6218997/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81060299,"identity":"9dc02631-384f-49d4-9ac8-b5eaeaaa2de4","added_by":"auto","created_at":"2025-04-21 18:46:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1474742,"visible":true,"origin":"","legend":"","description":"","filename":"Amultiscalefusionalgorithmforactionrecognition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6218997/v1_covered_4206b079-ea4e-41d3-8364-215183d7fc1e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMultiScale3D: A Multi-Scale Fusion Algorithm for Action Recognition\u003c/p\u003e","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":"Multiscale3D, Action recognition, Skeleton Keypoint detection, ResNet modules, YOLO-Pose","lastPublishedDoi":"10.21203/rs.3.rs-6218997/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6218997/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Camera-based behavior recognition is an effective means to prevent accidents. However, when a single camera is used to identify distant and close-range people's behaviors in a complex background, it is difficult to extract global and local features with different resolutions simultaneously, resulting in low recognition accuracy and slow recognition speed. In this paper, a multi-scale fusion motion recognition method, MultiScale3D, is proposed. First of all, based on YOLO-Pose technology, we put forward the remote and near synchronous bone key point extraction module, which improves the collaborative extraction speed of remote and near motion features. Then, a three-level ResNet module is designed to realize feature sampling with different resolutions, and the features of each level are splicing with the features of the other two levels respectively to achieve multi-scale feature fusion. The multi-scale information is weighted by the proposed MultiScale3D module, which further enhances the expression ability of key features. Among the experimental results of three public datasets, the model achieved an accuracy of 94.4% (state of arts) on NTU60-Xsub and 95.9% on FineGYM dataset. At the same time, the algorithm shows good robustness and generalization in the recognition of distant and close-range behaviors. Training code are available at https://github.com/Zhai-Mao/MultiScale3D","manuscriptTitle":"MultiScale3D: A Multi-Scale Fusion Algorithm for Action Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-15 04:15:53","doi":"10.21203/rs.3.rs-6218997/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":"be1345c7-9349-4b43-a257-1e7634d27597","owner":[],"postedDate":"April 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-04-21T18:38:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-15 04:15:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6218997","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6218997","identity":"rs-6218997","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}