MFFP-Net: Multi-directional Feature Fusion and Position-Aware Network

MFFP-Net: Multi-directional Feature Fusion and Position-Aware Network | 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 MFFP-Net: Multi-directional Feature Fusion and Position-Aware Network Yazhong Si, Jingyu Chen, Hongxu Li, Chen Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8783703/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 Vehicle re-identification faces significant challenges in feature modeling due to viewpoint variations, illumination changes, occlusions, and intra-class similarity. To this end, we propose a VeRi algorithm based on multi-directional feature fusion and position awareness, which synergistically integrates multi-dimensional features and positional information to suppress background interference and improve feature discriminability. Specifically, we design multi-directional depthwise separable convolution kernels which square kernels for local details, horizontal strip kernels for long-range dependencies, and vertical strip kernels for spatial distribution to capture comprehensive directional features; the DOConv module fuses depthwise convolution and conventional convolution to balance fine-grained texture extraction and global structural integration without additional sub-networks; and a position encoding module with horizontal-vertical tensor initialization enhances the model's perception of key components' relative positions. Experimental results on the VeRi-776 and Veri-Wild datasets demonstrate the superior performance of the proposed algorithm. Vehicle re-identification Multi-directional feature fusion Position awareness Depthwise separable convolution 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-8783703","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":600657586,"identity":"04d63994-7236-46b1-9d62-a6b84a4574fb","order_by":0,"name":"Yazhong Si","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYDACZiBmbAAxmA8/+GBgY0eCFna2NMMZBWnJxNkE1sLPYyDN8+EQmI0XyLfzGH78ucMmT96ZwcDYxuAAMwP74aMb8GkxOMxjLCF5Jq3Y8DBDwuMcgzt8DDxpaTfwamHmMZAwbDucuLGZ4YBxjsEzZgYJHjO8WuSbeYx/JIK1MDZIWxgcZmwgpIXhMI+ZxEGglvnMzAzSDMRoMTjMVmbZ2JaWuIGZjc2wxyAtmY2QX+T7D2+++bPNJnF+//nPD378sbHjZz98DL/DGDgMINYdgPLZ8CsHAfYHEOsaCCsdBaNgFIyCEQoAuLdJoUH7DBoAAAAASUVORK5CYII=","orcid":"","institution":"Wuxi University","correspondingAuthor":true,"prefix":"","firstName":"Yazhong","middleName":"","lastName":"Si","suffix":""},{"id":600657587,"identity":"efdba090-cc16-40c9-8ced-3b2016457658","order_by":1,"name":"Jingyu Chen","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jingyu","middleName":"","lastName":"Chen","suffix":""},{"id":600657588,"identity":"ed5be2d5-13ce-4072-b67c-4109b48cd0bb","order_by":2,"name":"Hongxu Li","email":"","orcid":"","institution":"Wuxi University","correspondingAuthor":false,"prefix":"","firstName":"Hongxu","middleName":"","lastName":"Li","suffix":""},{"id":600657589,"identity":"ad2abea1-be55-4c8c-95ff-b2a8b0bc38e9","order_by":3,"name":"Chen Li","email":"","orcid":"","institution":"Wuxi University","correspondingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2026-02-04 08:24:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8783703/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8783703/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108493278,"identity":"edfb4595-8401-4cbb-8c3e-d75085b36d12","added_by":"auto","created_at":"2026-05-05 09:59:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":545051,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8783703/v1_covered_d77ddc9b-af61-4639-8b8b-c811351e537a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"MFFP-Net: Multi-directional Feature Fusion and Position-Aware Network","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":"Vehicle re-identification, Multi-directional feature fusion, Position awareness, Depthwise separable convolution","lastPublishedDoi":"10.21203/rs.3.rs-8783703/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8783703/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eVehicle re-identification faces significant challenges in feature modeling due to viewpoint variations, illumination changes, occlusions, and intra-class similarity. To this end, we propose a VeRi algorithm based on multi-directional feature fusion and position awareness, which synergistically integrates multi-dimensional features and positional information to suppress background interference and improve feature discriminability. Specifically, we design multi-directional depthwise separable convolution kernels which square kernels for local details, horizontal strip kernels for long-range dependencies, and vertical strip kernels for spatial distribution to capture comprehensive directional features; the DOConv module fuses depthwise convolution and conventional convolution to balance fine-grained texture extraction and global structural integration without additional sub-networks; and a position encoding module with horizontal-vertical tensor initialization enhances the model's perception of key components' relative positions. Experimental results on the VeRi-776 and Veri-Wild datasets demonstrate the superior performance of the proposed algorithm.\u003c/p\u003e","manuscriptTitle":"MFFP-Net: Multi-directional Feature Fusion and Position-Aware Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-09 05:51:32","doi":"10.21203/rs.3.rs-8783703/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":"55d6f6f1-df15-4d41-bfb2-13363fc5c256","owner":[],"postedDate":"March 9th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-03T11:46:10+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-03T11:55:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-09 05:51:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8783703","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8783703","identity":"rs-8783703","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}