Modeling Body Part Interactions for Skeleton-Text Contrastive Learning in Action Recognition

Modeling Body Part Interactions for Skeleton-Text Contrastive Learning in 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 Modeling Body Part Interactions for Skeleton-Text Contrastive Learning in Action Recognition Shuang Liang, Ruihao Qian, Zikun Zhuang, Chi Xie This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4929315/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 Skeleton-based action recognition has garnered significant attention due to its efficiency and robustness. Recent advances in skeleton-text contrastive learning show promise but overlook interactions between skeleton parts. This paper proposes a part interaction module that models these interactions to align skeleton features with descriptive texts. Experiments demonstrate that incorporating this module leads to notable improvements, establishing a new state-of-the-art on popular benchmarks. Our work underscores the importance of part interactions for action recognition.Code is released at https://github.com/ReskyQian/Body-Part-Interactions . skeleton-based action recognition skeleton-text contrastive learning body part interaction cross-attention mechanism 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-4929315","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":349198819,"identity":"0328bd30-166c-4d34-b27b-c7ec3d7c5b66","order_by":0,"name":"Shuang Liang","email":"data:image/png;base64,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","orcid":"","institution":"Tongji University","correspondingAuthor":true,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Liang","suffix":""},{"id":349198820,"identity":"8559b5d8-9251-4420-b80c-e0c165ee8fe0","order_by":1,"name":"Ruihao Qian","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Ruihao","middleName":"","lastName":"Qian","suffix":""},{"id":349198821,"identity":"58fdafdb-4469-4bf8-8feb-88dd5ae356c1","order_by":2,"name":"Zikun Zhuang","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Zikun","middleName":"","lastName":"Zhuang","suffix":""},{"id":349198822,"identity":"524e58a4-a38c-4b38-be3e-bf97c6bb2991","order_by":3,"name":"Chi Xie","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Chi","middleName":"","lastName":"Xie","suffix":""}],"badges":[],"createdAt":"2024-08-17 10:24:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4929315/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4929315/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":86138923,"identity":"b9de471f-c8b6-4ca3-b5f7-f7a60881dfea","added_by":"auto","created_at":"2025-07-07 08:09:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1211177,"visible":true,"origin":"","legend":"","description":"","filename":"partinteractiontvc.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4929315/v1_covered_d4509424-4a74-40d9-a5d2-d4d3c5b2dd8f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Modeling Body Part Interactions for Skeleton-Text Contrastive Learning in Action Recognition","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":"skeleton-based action recognition, skeleton-text contrastive learning, body part interaction, cross-attention mechanism","lastPublishedDoi":"10.21203/rs.3.rs-4929315/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4929315/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Skeleton-based action recognition has garnered significant attention due to its efficiency and robustness. Recent advances in skeleton-text contrastive learning show promise but overlook interactions between skeleton parts. This paper proposes a part interaction module that models these interactions to align skeleton features with descriptive texts. Experiments demonstrate that incorporating this module leads to notable improvements, establishing a new state-of-the-art on popular benchmarks. Our work underscores the importance of part interactions for action recognition.Code is released at https://github.com/ReskyQian/Body-Part-Interactions.","manuscriptTitle":"Modeling Body Part Interactions for Skeleton-Text Contrastive Learning in Action Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-16 18:41:17","doi":"10.21203/rs.3.rs-4929315/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":"d591e5a1-7587-418b-b96e-4894f8ced6a1","owner":[],"postedDate":"September 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-07T08:09:08+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-16 18:41:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4929315","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4929315","identity":"rs-4929315","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}