Diving Performance Analysis with 3D Motion Knowledge Hypergraphs

Diving Performance Analysis with 3D Motion Knowledge Hypergraphs | 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 Diving Performance Analysis with 3D Motion Knowledge Hypergraphs Jingbo Wang, Yifan Xie, Yitao Xie, Hongyu Xiao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6812566/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Diving actions involve complex temporal dynamics, rapid pose transitions, and strict requirements for entry angles and splash control, making quality assessment a challenging task in computer vision. Existing methods still face limitations in motion structure modeling, depth perception, and multimodal fusion. This paper proposes a multimodal scoring framework that integrates 3D pose reconstruction with a hypergraph neural network to enhance the modeling and evaluation of diving actions. We are the first to introduce 3D pose reconstruction into diving score assessment, compensating for the depth perception limitations of 2D vision by constructing complete 3D motion trajectories. To mitigate keypoint errors caused by rapid movements or occlusions, we propose a hypergraph-based spatiotemporal pose fusion model. This model leverages three types of hyperedges—temporal, skeletal, and joint—to build high-order spatiotemporal representations, and incorporates an attention mechanism to adaptively adjust their weights. To capture visual cues such as entry angles and splash patterns, we further design a multimodal fusion module that combines skeletal features with appearance features, significantly enhancing the model’s ability to perceive fine details. To address the lack of structured and fine-grained annotations in existing datasets, we also construct the Individual-Diving dataset, which contains 1,023 diving video clips covering 27 action classes, 26 sub-actions, along with frame-wise 3D pose annotations and official scores. Experimental results on the FineDiving and Individual-Diving datasets show that our method consistently outperforms previous approaches such as USDL and CoRe, demonstrating competitive performance in diving action modeling and quality assessment. Deep Learning 3D Keypoints Hypergraph Neural Network Diving Motion Analysis Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 25 Dec, 2025 Reviews received at journal 24 Dec, 2025 Reviewers agreed at journal 23 Dec, 2025 Reviewers agreed at journal 06 Dec, 2025 Reviews received at journal 27 Oct, 2025 Reviewers agreed at journal 12 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviewers agreed at journal 02 Sep, 2025 Reviewers invited by journal 02 Sep, 2025 Editor assigned by journal 14 Jul, 2025 Submission checks completed at journal 05 Jun, 2025 First submitted to journal 03 Jun, 2025 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-6812566","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":511382476,"identity":"a40f4566-2e09-4870-b1a7-4cf31afe17cf","order_by":0,"name":"Jingbo Wang","email":"","orcid":"","institution":"Beijing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jingbo","middleName":"","lastName":"Wang","suffix":""},{"id":511382477,"identity":"4ab08c01-f5ac-4630-9129-eaac9ebf16f3","order_by":1,"name":"Yifan Xie","email":"","orcid":"","institution":"University of Glasgow","correspondingAuthor":false,"prefix":"","firstName":"Yifan","middleName":"","lastName":"Xie","suffix":""},{"id":511382478,"identity":"bc81d00f-9639-4514-aa62-e32a998fc6be","order_by":2,"name":"Yitao Xie","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Yitao","middleName":"","lastName":"Xie","suffix":""},{"id":511382479,"identity":"bac44bff-7307-445d-a6a1-58fa48e65a06","order_by":3,"name":"Hongyu Xiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYDACCQbGxxBWAvFamI1J1sImTZoWg9s9ZtWFOw4z8LPnGDD83EGEFsk5Z8xuzzxzmEGy540BY+8ZIrTwS+SY3eZtO8xgcCPHgJmxjQgtbEAtxSAt9kRrAdnCDLZFglgtkjPSiqVntqXzSJx5VnCwlxgtBjeSN34ubLOW429P3vjgJzFaGBg4DEAkD4g4QJQGBgb2B0QqHAWjYBSMghELACQwMCYkqVFZAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing Normal University","correspondingAuthor":true,"prefix":"","firstName":"Hongyu","middleName":"","lastName":"Xiao","suffix":""}],"badges":[],"createdAt":"2025-06-03 14:53:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6812566/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6812566/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90774098,"identity":"b6ffa7e4-2e16-4aa1-b14b-815491be1f9d","added_by":"auto","created_at":"2025-09-08 02:30:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1480805,"visible":true,"origin":"","legend":"","description":"","filename":"DivingPerformanceAnalysiswith3DMotionKnowledgeHypergraphsMultimediaSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6812566/v1_covered_1542327c-9cdd-4ab1-8e9b-04cafad4a099.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Diving Performance Analysis with 3D Motion Knowledge Hypergraphs","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Deep Learning, 3D Keypoints, Hypergraph Neural Network, Diving Motion Analysis","lastPublishedDoi":"10.21203/rs.3.rs-6812566/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6812566/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDiving actions involve complex temporal dynamics, rapid pose transitions, and strict requirements for entry angles and splash control, making quality assessment a challenging task in computer vision. Existing methods still face limitations in motion structure modeling, depth perception, and multimodal fusion. This paper proposes a multimodal scoring framework that integrates 3D pose reconstruction with a hypergraph neural network to enhance the modeling and evaluation of diving actions. We are the first to introduce 3D pose reconstruction into diving score assessment, compensating for the depth perception limitations of 2D vision by constructing complete 3D motion trajectories. To mitigate keypoint errors caused by rapid movements or occlusions, we propose a hypergraph-based spatiotemporal pose fusion model. This model leverages three types of hyperedges\u0026mdash;temporal, skeletal, and joint\u0026mdash;to build high-order spatiotemporal representations, and incorporates an attention mechanism to adaptively adjust their weights. To capture visual cues such as entry angles and splash patterns, we further design a multimodal fusion module that combines skeletal features with appearance features, significantly enhancing the model\u0026rsquo;s ability to perceive fine details. To address the lack of structured and fine-grained annotations in existing datasets, we also construct the Individual-Diving dataset, which contains 1,023 diving video clips covering 27 action classes, 26 sub-actions, along with frame-wise 3D pose annotations and official scores. Experimental results on the FineDiving and Individual-Diving datasets show that our method consistently outperforms previous approaches such as USDL and CoRe, demonstrating competitive performance in diving action modeling and quality assessment.\u003c/p\u003e","manuscriptTitle":"Diving Performance Analysis with 3D Motion Knowledge Hypergraphs","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-08 01:58:06","doi":"10.21203/rs.3.rs-6812566/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-26T01:40:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-24T13:19:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"20758603757562805595054598060190134383","date":"2025-12-24T02:28:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"140786883245513407530843064768940308601","date":"2025-12-06T13:10:59+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-27T09:55:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326679038851223186716971440781644701559","date":"2025-09-12T09:59:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"166795692646312066437797732332671325869","date":"2025-09-07T10:15:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"66190424761405759272496591241317717770","date":"2025-09-02T10:36:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-02T10:12:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-14T07:28:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-05T14:08:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-06-03T14:47:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e81dcc9b-3d72-4844-b6a9-7a8cc10d4bfd","owner":[],"postedDate":"September 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-06T17:09:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-08 01:58:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6812566","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6812566","identity":"rs-6812566","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}