Central Attention with Sliding Window for Efficient Visual Tracking

Central Attention with Sliding Window for Efficient Visual Tracking | 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 Central Attention with Sliding Window for Efficient Visual Tracking Zhen Chen, Xianbing Xiao, Xingzhong Xiong, Fanqin Meng, Jun Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3912795/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 Cross-correlation is often used for feature fusion, especially in Siamese-based trackers. However, capturing complex nonlinear relationships is challenging and susceptible to outliers in the sample. Recently, researchers have used Transformers for feature fusion and achieved more significant performance. However, most rely on modeling global token relationships, which can destroy the local and spatial correlations inherent in 2D structures. This paper proposes an efficient tracking algorithm based on central attention and sliding window sampling called SiamCAT. Specifically, significant context augments with sliding windows are suggested to maintain the stability of the 2D input spatial structure. It is based on attention to simulate the processing of 2D data by convolution, and the internal memory composed of learnable parameters realizes the dynamic adjustment of the attention layer. Second, to learn efficient feature fusion, this paper constructs a feature fusion network to effectively combine template features and search features. Experiments show that SiamCAT achieves state-of-the-art results on LaSOT, OTB100, NFS, UAV123, GOT10K, and TrackingNet benchmark and runs in real-time at 47 frames per second on the CPU. The code will be released in https://github.com/cnchange/SiamCAT . Object tracking Transformer Real-time tracking Deep learning 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-3912795","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":270269683,"identity":"8f8c8532-bc54-4746-9bf6-014f66937ab5","order_by":0,"name":"Zhen Chen","email":"data:image/png;base64,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","orcid":"","institution":"Sichuan University of Science and Engineering","correspondingAuthor":true,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Chen","suffix":""},{"id":270269684,"identity":"a202e2f6-78e8-4491-aaa5-4e0e52127b2e","order_by":1,"name":"Xianbing Xiao","email":"","orcid":"","institution":"Sichuan University of Science and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Xianbing","middleName":"","lastName":"Xiao","suffix":""},{"id":270269685,"identity":"df838250-7dfd-47a8-9cbf-02967f904266","order_by":2,"name":"Xingzhong Xiong","email":"","orcid":"","institution":"Sichuan University of Science and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Xingzhong","middleName":"","lastName":"Xiong","suffix":""},{"id":270269686,"identity":"277cb485-235b-4bad-8074-8ed965277d98","order_by":3,"name":"Fanqin Meng","email":"","orcid":"","institution":"Sichuan University of Science and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Fanqin","middleName":"","lastName":"Meng","suffix":""},{"id":270269687,"identity":"727ebd91-85a8-4ea1-93b8-331ceb6c6921","order_by":4,"name":"Jun Liu","email":"","orcid":"","institution":"Sichuan University of Science and Engineering","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-01-31 06:17:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3912795/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3912795/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52381645,"identity":"5569f3b7-73b2-43a1-802b-85664a6ef654","added_by":"auto","created_at":"2024-03-10 17:18:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4747051,"visible":true,"origin":"","legend":"","description":"","filename":"SiamCAT.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3912795/v1_covered_e35e13c5-c746-44e4-9d81-3252bb0c2d73.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Central Attention with Sliding Window for Efficient Visual Tracking","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":"Object tracking, Transformer, Real-time tracking, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-3912795/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3912795/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCross-correlation is often used for feature fusion, especially in Siamese-based trackers. However, capturing complex nonlinear relationships is challenging and susceptible to outliers in the sample. Recently, researchers have used Transformers for feature fusion and achieved more significant performance. However, most rely on modeling global token relationships, which can destroy the local and spatial correlations inherent in 2D structures. This paper proposes an efficient tracking algorithm based on central attention and sliding window sampling called SiamCAT. Specifically, significant context augments with sliding windows are suggested to maintain the stability of the 2D input spatial structure. It is based on attention to simulate the processing of 2D data by convolution, and the internal memory composed of learnable parameters realizes the dynamic adjustment of the attention layer. Second, to learn efficient feature fusion, this paper constructs a feature fusion network to effectively combine template features and search features. Experiments show that SiamCAT achieves state-of-the-art results on LaSOT, OTB100, NFS, UAV123, GOT10K, and TrackingNet benchmark and runs in real-time at 47 frames per second on the CPU. The code will be released in \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/cnchange/SiamCAT\u003c/span\u003e\u003cspan address=\"https://github.com/cnchange/SiamCAT\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"Central Attention with Sliding Window for Efficient Visual Tracking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-02 16:05:13","doi":"10.21203/rs.3.rs-3912795/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":"9538413a-b5be-467c-818b-6d67efca5bd1","owner":[],"postedDate":"February 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-03-10T17:09:15+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-02 16:05:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3912795","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3912795","identity":"rs-3912795","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}