Target-background interaction prompt framework for target tracking

Target-background interaction prompt framework for target 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 Target-background interaction prompt framework for target tracking Huanlong Zhang, Junlong Gao, Weiqiang Fu, Linwei Li, Wanguo Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7288675/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Jan, 2026 Read the published version in Signal, Image and Video Processing → Version 1 posted 9 You are reading this latest preprint version Abstract How to effectively exploit spatio-temporal information is crucial for accurate target localisation in visual tracking. However, most existing trackers attempt to devise complex appearance models or template updating strategies, while neglecting the mining of the relationship between the target and the background. To address these issues, we propose a novel target-background interaction prompt framework for visual tracking, called TBPTrack. Firstly, we design a multi-scale target-background feature extraction module, which can fully excavate the features of target-background on more and applicable scales, and relax the influence caused by the appearance change of target. Secondly, a target-background prompt generator is presented, which utilises target-background tokens to generate explicit visual prompts that promote inferences in the current frame. The introduction of background tokens can not only enhance the representation of targets, but also weaken the interference of similar objects inter-class. Finally, a spatio-temporal scenario module is designed, utilising spatio-temporal tokens to propagate information between consecutive frames without the necessity of updating templates. This alleviates the challenge of determining the optimal moment for template updating. Extensive experimentation in seven benchmark tests demonstrates the effectiveness of the proposed method in comparison to existing state-of-the-art trackers. Object tracking Target-background interaction Spatio-temporal information Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Jan, 2026 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 01 Oct, 2025 Reviews received at journal 19 Sep, 2025 Reviewers agreed at journal 15 Sep, 2025 Reviews received at journal 02 Sep, 2025 Reviewers agreed at journal 22 Aug, 2025 Reviewers invited by journal 22 Aug, 2025 Editor assigned by journal 13 Aug, 2025 Submission checks completed at journal 13 Aug, 2025 First submitted to journal 04 Aug, 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-7288675","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":506244718,"identity":"50b7bed5-24ea-4f51-8fe5-0c1e2dffc84c","order_by":0,"name":"Huanlong Zhang","email":"","orcid":"","institution":"Zhengzhou University of Light Industry","correspondingAuthor":false,"prefix":"","firstName":"Huanlong","middleName":"","lastName":"Zhang","suffix":""},{"id":506244719,"identity":"28b1d1bf-28d6-42cb-9510-44925c1b0455","order_by":1,"name":"Junlong Gao","email":"","orcid":"","institution":"Zhengzhou University of Light Industry","correspondingAuthor":false,"prefix":"","firstName":"Junlong","middleName":"","lastName":"Gao","suffix":""},{"id":506244721,"identity":"2ef5ceb5-640c-452d-98d8-504a37a2f210","order_by":2,"name":"Weiqiang Fu","email":"","orcid":"","institution":"Zhengzhou University of Light Industry","correspondingAuthor":false,"prefix":"","firstName":"Weiqiang","middleName":"","lastName":"Fu","suffix":""},{"id":506244722,"identity":"bfc58ab9-dd45-419b-9012-fe9f78ca4e02","order_by":3,"name":"Linwei Li","email":"","orcid":"","institution":"Zhengzhou University of Light Industry","correspondingAuthor":false,"prefix":"","firstName":"Linwei","middleName":"","lastName":"Li","suffix":""},{"id":506244723,"identity":"403f8c2a-8636-4f70-b120-e6f9b11730d5","order_by":4,"name":"Wanguo Wang","email":"","orcid":"","institution":"State Grid Intelligence Technology Co., Ltd., Jinan 250101, Shandong, China","correspondingAuthor":false,"prefix":"","firstName":"Wanguo","middleName":"","lastName":"Wang","suffix":""},{"id":506244727,"identity":"1cf41b38-a5df-4a02-91a6-b13fe221488d","order_by":5,"name":"Yanfeng Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIie2QsQrCMBRFHwjFodBNIg75hRRBHaTFP0npDzhJx3ZxKri2+BNOzpEHneIu6FAQnBwydjS2e5tRMGe5BO7hkgdgsfwkAqDW4QEKoRpTheuYZlV0KXPToa/CUM5x7Bi06UYuap48grSSCsEF6k1Ev+ILuWRcvuIsv55wuwK/PPIBJZULEu0xHhGtFC5wdjdVHPqu0XUMFAqdErggwUxhUO0Il8gJVEwfmQz/hRZ4JirBMBT4VKpZU282tHITbUZp9yb99Xbl0HXD4arFYrH8LR8qXVCrjOeQxgAAAABJRU5ErkJggg==","orcid":"","institution":"Zhengzhou University of Light Industry","correspondingAuthor":true,"prefix":"","firstName":"Yanfeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-08-04 08:23:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7288675/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7288675/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-05083-7","type":"published","date":"2026-01-16T16:30:22+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100615926,"identity":"37e0d5e5-2d92-44ef-b7ef-53e0077fee87","added_by":"auto","created_at":"2026-01-19 17:38:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1546469,"visible":true,"origin":"","legend":"","description":"","filename":"manscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7288675/v1_covered_622bf6aa-8983-41fd-979d-321696d76986.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Target-background interaction prompt framework for target tracking ","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Object tracking, Target-background interaction, Spatio-temporal information","lastPublishedDoi":"10.21203/rs.3.rs-7288675/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7288675/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHow to effectively exploit spatio-temporal information is crucial for accurate target localisation in visual tracking. However, most existing trackers attempt to devise complex appearance models or template updating strategies, while neglecting the mining of the relationship between the target and the background. To address these issues, we propose a novel target-background interaction prompt framework for visual tracking, called TBPTrack. Firstly, we design a multi-scale target-background feature extraction module, which can fully excavate the features of target-background on more and applicable scales, and relax the influence caused by the appearance change of target. Secondly, a target-background prompt generator is presented, which utilises target-background tokens to generate explicit visual prompts that promote inferences in the current frame. The introduction of background tokens can not only enhance the representation of targets, but also weaken the interference of similar objects inter-class. Finally, a spatio-temporal scenario module is designed, utilising spatio-temporal tokens to propagate information between consecutive frames without the necessity of updating templates. This alleviates the challenge of determining the optimal moment for template updating. Extensive experimentation in seven benchmark tests demonstrates the effectiveness of the proposed method in comparison to existing state-of-the-art trackers.\u003c/p\u003e","manuscriptTitle":"Target-background interaction prompt framework for target tracking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-02 19:09:22","doi":"10.21203/rs.3.rs-7288675/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-01T08:47:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-19T07:22:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"192586791519878910526522249317732106396","date":"2025-09-16T01:15:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-02T06:38:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"339630017576680118699762161918511819191","date":"2025-08-22T08:39:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-22T07:52:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-13T06:09:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-13T06:06:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-08-04T08:16:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"afce9070-a8d3-48db-98fe-d8848650f96e","owner":[],"postedDate":"September 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-19T17:04:37+00:00","versionOfRecord":{"articleIdentity":"rs-7288675","link":"https://doi.org/10.1007/s11760-025-05083-7","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2026-01-16 16:30:22","publishedOnDateReadable":"January 16th, 2026"},"versionCreatedAt":"2025-09-02 19:09:22","video":"","vorDoi":"10.1007/s11760-025-05083-7","vorDoiUrl":"https://doi.org/10.1007/s11760-025-05083-7","workflowStages":[]},"version":"v1","identity":"rs-7288675","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7288675","identity":"rs-7288675","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}