Language-Driven 3D Skeleton-Based Motion Generation with Action Nesting Graph

Language-Driven 3D Skeleton-Based Motion Generation with Action Nesting Graph | 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 Language-Driven 3D Skeleton-Based Motion Generation with Action Nesting Graph Oliver J. Hart, Mia L. Franklin, Thomas R. Shields, Emily K. Dawson This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7467247/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 To address the task of generating human motion from complex natural language instructions, this paper proposes a 3D skeleton-based motion generation method that integrates an action nesting graph. The method first constructs the action nesting graph through a language parsing module to capture the segmented structure of actions in the instruction. Then, a graph convolutional neural network is used to model the correspondence between the nested structure and the keyframes of the skeleton. A stage-wise decoupling module is introduced to improve the naturalness of motion transitions. On the KIT Motion and BEAT-Motion datasets, this method achieves improvements of 14.7% in structural preservation rate and 10.2% in stage boundary consistency. The results demonstrate that the proposed nesting-based modeling mechanism effectively enhances the model’s ability to interpret complex composite actions and improves the quality of motion generation Artificial Intelligence and Machine Learning Action nesting graph Language understanding 3D skeleton modeling Motion segmentation Graph neural network Instruction parsing Motion structure modeling Full Text Additional Declarations The authors declare no competing interests. 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-7467247","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":506118226,"identity":"f8326fc8-1059-4554-b597-c1458ce3316c","order_by":0,"name":"Oliver J. Hart","email":"","orcid":"","institution":"Department of Computer Science, University College London (UCL), United Kingdom","correspondingAuthor":false,"prefix":"","firstName":"Oliver","middleName":"J.","lastName":"Hart","suffix":""},{"id":506118227,"identity":"fd4cef31-840b-4137-8bea-7cbe640a1c4d","order_by":1,"name":"Mia L. Franklin","email":"","orcid":"","institution":"Department of Computer Science, University College London (UCL), United Kingdom","correspondingAuthor":false,"prefix":"","firstName":"Mia","middleName":"L.","lastName":"Franklin","suffix":""},{"id":506118228,"identity":"9f7cb26d-fa52-4b2c-812b-e32e1f2242d0","order_by":2,"name":"Thomas R. Shields","email":"","orcid":"","institution":"Centre for Artificial Intelligence, Queen Mary University of London, United Kingdom","correspondingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"R.","lastName":"Shields","suffix":""},{"id":506118229,"identity":"a43d1482-7dae-474f-a335-aafed47df80a","order_by":3,"name":"Emily K. Dawson","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIie2RvQrCMBCAT4S6BLqmU14hoVAQSp/loBAfwEVx8EDQ19E3iHRwiXWWLk7OBRfd7A+ubd0E8w3HDfeRDwLgcPwkth5xu9+a6Q1RULc7DlNYfZp9ofij8/GxfF6EIKZKhEQA19ipBJSngcVC7Q0LOUKqiGvTqUhjZUBYoAQWVWFjBD6jPiV8EeZYhdXKepASVa8YBNMoWaX0hAVkoynpVO0zb85RntSW3bFT8bkNrxQnQuw2h7JcrIQ/0bJTAf6pGDedAz4SfOo9cTgcjn/nDSH1P4C9/dT2AAAAAElFTkSuQmCC","orcid":"","institution":"Centre for Artificial Intelligence, Queen Mary University of London, United Kingdom","correspondingAuthor":true,"prefix":"","firstName":"Emily","middleName":"K.","lastName":"Dawson","suffix":""}],"badges":[],"createdAt":"2025-08-27 03:03:40","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7467247/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7467247/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90142141,"identity":"ca2748e3-f021-45f7-88dd-878f63f4d576","added_by":"auto","created_at":"2025-08-29 04:13:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":389014,"visible":true,"origin":"","legend":"","description":"","filename":"112LanguageDriven3DSkeletonBasedMotionGenerationwithActionNestingGraph.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7467247/v1_covered_c7280125-7dbf-48f4-aea1-a4537a7b80a3.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eLanguage-Driven 3D Skeleton-Based Motion Generation with Action Nesting Graph\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Action nesting graph, Language understanding, 3D skeleton modeling, Motion segmentation, Graph neural network, Instruction parsing, Motion structure modeling","lastPublishedDoi":"10.21203/rs.3.rs-7467247/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7467247/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the task of generating human motion from complex natural language instructions, this paper proposes a 3D skeleton-based motion generation method that integrates an action nesting graph. The method first constructs the action nesting graph through a language parsing module to capture the segmented structure of actions in the instruction. Then, a graph convolutional neural network is used to model the correspondence between the nested structure and the keyframes of the skeleton. A stage-wise decoupling module is introduced to improve the naturalness of motion transitions. On the KIT Motion and BEAT-Motion datasets, this method achieves improvements of 14.7% in structural preservation rate and 10.2% in stage boundary consistency. The results demonstrate that the proposed nesting-based modeling mechanism effectively enhances the model’s ability to interpret complex composite actions and improves the quality of motion generation\u003c/p\u003e","manuscriptTitle":"Language-Driven 3D Skeleton-Based Motion Generation with Action Nesting Graph","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-29 04:04:57","doi":"10.21203/rs.3.rs-7467247/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":"46064230-d23c-4308-b4d5-03c93de852ac","owner":[],"postedDate":"August 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53759126,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-08-29T04:04:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-29 04:04:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7467247","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7467247","identity":"rs-7467247","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}