DSTAdapter:Divided Spatial-Temporal Adapter Fine-tuning Method for Sign Language Recognition

DSTAdapter:Divided Spatial-Temporal Adapter Fine-tuning Method for Sign Language 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 DSTAdapter:Divided Spatial-Temporal Adapter Fine-tuning Method for Sign Language Recognition Qiuhong Tian, Yijie Yang, Bin Chen, Jiacheng Chen, Junxiao Ning, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6259023/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Mar, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted 9 You are reading this latest preprint version Abstract The commonly adopted approach of full fine-tuning for video-based sign language recognition models encounters two critical limitations: high computational resource consumption and compromised generalization capabilities. To address these challenges, we propose DSTAdapter, a parameter-efficient transfer learning framework that activates frozen CLIP models for video understanding through spatial-temporal decoupled adaptation. Our methodology introduces three key technical contributions: (1) dual-branch adapter architecture with separate adapter branches dedicated to capturing spatial hand shapes and temporal gesture dynamics, (2) channel-aware feature fusion modules that dynamically optimize the interaction between adapter-enhanced features and backbone representations, and (3) a lightweight framework design enabling efficient deployment on resource-constrained devices. Requiring only 4% tunable parameters, the proposed method establishes new state-of-the-art performance across four benchmark sign language datasets. Comprehensive evaluations demonstrate significant efficiency improvements, particularly on the Bukva benchmark where DSTAdapter achieves a 30% reduction in training time and 60% decrease in GPU memory consumption compared to conventional full fine-tuning approaches. The compact architecture further facilitates practical multitask deployment scenarios. These technical advancements present a promising solution for developing real-world assistive technologies, particularly benefiting hearing-impaired communities through improved accessibility. The code of this work is available at https://github.com/BLOOM0-0/DSTAdapter. Parameter efficiency Sign language recognition Low training cost Decoupled spatial-temporal Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Mar, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted Editorial decision: Revision requested 07 Apr, 2025 Reviews received at journal 06 Apr, 2025 Reviews received at journal 28 Mar, 2025 Reviewers agreed at journal 22 Mar, 2025 Reviewers agreed at journal 21 Mar, 2025 Reviewers invited by journal 20 Mar, 2025 Editor assigned by journal 20 Mar, 2025 Submission checks completed at journal 19 Mar, 2025 First submitted to journal 19 Mar, 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-6259023","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":432608839,"identity":"4fc410e6-e0ff-4f3c-a5e7-2be56343106e","order_by":0,"name":"Qiuhong Tian","email":"","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Qiuhong","middleName":"","lastName":"Tian","suffix":""},{"id":432608840,"identity":"34311024-01b0-441e-b66f-4cf7091224dc","order_by":1,"name":"Yijie Yang","email":"","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Yijie","middleName":"","lastName":"Yang","suffix":""},{"id":432608841,"identity":"ee95ff02-e12f-45ba-96a4-cdc7475c43cf","order_by":2,"name":"Bin Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIie3PMQuCQBjG8ScEWw5aD6T8CheCBH4ZRdBFy7Gh4SJwbT1o6KsYBzfZ7tAWNDc1RZS1NNm1Bd1/OV54f7wcYDL9YhSwwDACqna09In3LQEi/ho1yGCzUseiOKTbZe1TzIOI9/dV95GDSj3BTvmSq4SiTiNOpmEnYTTzHcJkvoJUtFfKiFPCPpDZpSWpjV1JezctktktCcnzCtcgtEl8RzA5FlDxJHx8rCRZNxmI+OQUV+m6oh4350UwXPfrbvJ2rwLCx2tr7rf3uP6uyWQy/Vd3Pt1AtHQK1DEAAAAASUVORK5CYII=","orcid":"","institution":"Jiaxing University","correspondingAuthor":true,"prefix":"","firstName":"Bin","middleName":"","lastName":"Chen","suffix":""},{"id":432608842,"identity":"d3d72ea5-117c-44f0-8537-cde68f9b0192","order_by":3,"name":"Jiacheng Chen","email":"","orcid":"","institution":"Jiaxing University","correspondingAuthor":false,"prefix":"","firstName":"Jiacheng","middleName":"","lastName":"Chen","suffix":""},{"id":432608843,"identity":"079a8107-c1a0-47c2-ad63-d77a3b793142","order_by":4,"name":"Junxiao Ning","email":"","orcid":"","institution":"Shaanxi University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Junxiao","middleName":"","lastName":"Ning","suffix":""},{"id":432608844,"identity":"64c947a5-c128-4d75-94c0-00532ae3c188","order_by":5,"name":"Lizao Zhang","email":"","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Lizao","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-03-19 07:38:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6259023/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6259023/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13042-026-03002-x","type":"published","date":"2026-03-21T15:58:45+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":105224229,"identity":"47b4bb6b-756a-4e3f-b961-75ce37747489","added_by":"auto","created_at":"2026-03-23 16:13:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2156849,"visible":true,"origin":"","legend":"","description":"","filename":"DSTAdapterDividedSpatialTemporalAdapterFinetuingMethodinSignLanguageRecogonition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6259023/v1_covered_0aaec00a-7656-4bb3-9865-c5b218e76490.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DSTAdapter:Divided Spatial-Temporal Adapter Fine-tuning Method for Sign Language Recognition","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Parameter efficiency, Sign language recognition, Low training cost, Decoupled spatial-temporal","lastPublishedDoi":"10.21203/rs.3.rs-6259023/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6259023/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe commonly adopted approach of full fine-tuning for video-based sign language recognition models encounters two critical limitations: high computational resource consumption and compromised generalization capabilities. To address these challenges, we propose DSTAdapter, a parameter-efficient transfer learning framework that activates frozen CLIP models for video understanding through spatial-temporal decoupled adaptation. Our methodology introduces three key technical contributions: (1) dual-branch adapter architecture with separate adapter branches dedicated to capturing spatial hand shapes and temporal gesture dynamics, (2) channel-aware feature fusion modules that dynamically optimize the interaction between adapter-enhanced features and backbone representations, and (3) a lightweight framework design enabling efficient deployment on resource-constrained devices. Requiring only 4% tunable parameters, the proposed method establishes new state-of-the-art performance across four benchmark sign language datasets. Comprehensive evaluations demonstrate significant efficiency improvements, particularly on the Bukva benchmark where DSTAdapter achieves a 30% reduction in training time and 60% decrease in GPU memory consumption compared to conventional full fine-tuning approaches. The compact architecture further facilitates practical multitask deployment scenarios. These technical advancements present a promising solution for developing real-world assistive technologies, particularly benefiting hearing-impaired communities through improved accessibility. The code of this work is available at https://github.com/BLOOM0-0/DSTAdapter.\u003c/p\u003e","manuscriptTitle":"DSTAdapter:Divided Spatial-Temporal Adapter Fine-tuning Method for Sign Language Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-24 04:55:54","doi":"10.21203/rs.3.rs-6259023/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-07T11:10:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-06T13:49:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-28T09:00:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"18783499602142232249952615613504150494","date":"2025-03-22T14:18:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"325800598274465915195724619021003121101","date":"2025-03-21T15:52:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-21T03:46:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-21T01:13:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-19T15:09:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2025-03-19T07:26:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"64fa38eb-f85b-463c-bdea-9160babaaffe","owner":[],"postedDate":"March 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-23T16:08:10+00:00","versionOfRecord":{"articleIdentity":"rs-6259023","link":"https://doi.org/10.1007/s13042-026-03002-x","journal":{"identity":"international-journal-of-machine-learning-and-cybernetics","isVorOnly":false,"title":"International Journal of Machine Learning and Cybernetics"},"publishedOn":"2026-03-21 15:58:45","publishedOnDateReadable":"March 21st, 2026"},"versionCreatedAt":"2025-03-24 04:55:54","video":"","vorDoi":"10.1007/s13042-026-03002-x","vorDoiUrl":"https://doi.org/10.1007/s13042-026-03002-x","workflowStages":[]},"version":"v1","identity":"rs-6259023","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6259023","identity":"rs-6259023","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}