Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification

Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification | 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 Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification Zelin Deng, Yun Song, Siyuan Xu, Ke Nai, Huimiao Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7686860/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Multimedia Systems → Version 1 posted 12 You are reading this latest preprint version Abstract Visible-infrared person re-identification aims to identify person images between infrared and visible cameras. Existing methods generally embed shared features and specific features into the same space directly, which may impair the high discriminative features and therefore limit the recognition accuracy. To address this issue, this paper proposes a channel-level feature selection and fusion network (CFSFNet), in which the contributions of features are evaluated at the channel level for weighted fusion to enhance the discriminability of the features. The proposed CFSFNet consists of three main components including a feature extraction module (FEM), a feature selection module (FSM), and a channel-level feature fusion module (CFFM). Modality-shared and modality-specific features are first extracted by different multi-channel feature extractors in the FEM. The contributions of different features to identification are then evaluated at the channel level in the FSM. According to their contributions, modality-shared and modality-specific features are combined on selected high-response channels by a dual-channel-attention mean-weighted fusion in the CFFM. Through the collaboration between the CFFM and the FSM, the proposed method not only exploits both modality-shared properties and modality-specific characteristics but enhances the high discriminative features. Moreover, a novel tri-directional center triplet loss is proposed to combine with other loss constraints to guide the model to tighten the intra-class individuals and widen the inter-class gaps. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the superiority of the proposed method over state-of-the-art methods. Ablation studies also illustrate the effectiveness of each component of the proposed network. The source code of this work is publicly available at https://github.com/CV-ReID/CFSFNet . Visible-infrared person re-identification crossmodality fusion modality-specific feature channel-level feature selection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 08 Dec, 2025 Reviews received at journal 03 Dec, 2025 Reviews received at journal 26 Nov, 2025 Reviewers agreed at journal 18 Nov, 2025 Reviewers agreed at journal 18 Nov, 2025 Reviews received at journal 16 Nov, 2025 Reviewers agreed at journal 04 Nov, 2025 Reviewers agreed at journal 04 Nov, 2025 Reviewers invited by journal 04 Nov, 2025 Editor assigned by journal 02 Nov, 2025 Submission checks completed at journal 26 Sep, 2025 First submitted to journal 22 Sep, 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-7686860","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":540115364,"identity":"82bceb17-7205-49ae-9474-6d536904b85b","order_by":0,"name":"Zelin Deng","email":"","orcid":"","institution":"Changsha University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zelin","middleName":"","lastName":"Deng","suffix":""},{"id":540115365,"identity":"f91a2422-b699-40dd-b156-f2eced5798d8","order_by":1,"name":"Yun Song","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoElEQVRIiWNgGAWjYJCCAwwVEnL8JGo5Y2Es2UCSHsa2isQNRGuRb+89eODjPAnGDQzMDx/dIEaLwZlzCQdnbpNgNmdgMzbOIUqLRI7BYd5tEmyWDTxs0kRpkZ8B1PJ3jgSPwQFitTDcAGphbJCQIF6LwZkzBgd7jkkYSDYT6xf59h7jDz9q6ur72ZsfPibOYXDATJryUTAKRsEoGAX4AACy7i8s4Dp2WwAAAABJRU5ErkJggg==","orcid":"","institution":"Changsha University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Yun","middleName":"","lastName":"Song","suffix":""},{"id":540115366,"identity":"99839b7a-364d-4518-9478-ff3d6eaae4d0","order_by":2,"name":"Siyuan Xu","email":"","orcid":"","institution":"Changsha University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Siyuan","middleName":"","lastName":"Xu","suffix":""},{"id":540115367,"identity":"89a2eb6d-a635-4d6a-bbb7-1cebef612e54","order_by":3,"name":"Ke Nai","email":"","orcid":"","institution":"Changsha University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Nai","suffix":""},{"id":540115372,"identity":"f9b66e08-1186-4ef3-a37b-faf7c17ad33a","order_by":4,"name":"Huimiao Wang","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Huimiao","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-09-23 01:38:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7686860/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7686860/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02205-6","type":"published","date":"2026-02-03T15:58:36+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95276590,"identity":"f513a05e-fea3-4f6c-8119-abbfd849b130","added_by":"auto","created_at":"2025-11-06 08:30:13","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6824,"visible":true,"origin":"","legend":"","description":"","filename":"bd14a73943344f2db39b5deaa862e1b6.json","url":"https://assets-eu.researchsquare.com/files/rs-7686860/v1/7f4dc23e889b89cba51f153a.json"},{"id":102235152,"identity":"5f7daabe-2ceb-40d4-85bb-72b4e5d9cb78","added_by":"auto","created_at":"2026-02-09 16:15:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1360733,"visible":true,"origin":"","legend":"","description":"","filename":"latex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7686860/v1_covered_eb8d706b-ae55-4b7e-8a03-213de188ad59.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification","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":"Visible-infrared person re-identification, crossmodality fusion, modality-specific feature, channel-level feature selection","lastPublishedDoi":"10.21203/rs.3.rs-7686860/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7686860/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Visible-infrared person re-identification aims to identify person images between infrared and visible cameras. Existing methods generally embed shared features and specific features into the same space directly, which may impair the high discriminative features and therefore limit the recognition accuracy. To address this issue, this paper proposes a channel-level feature selection and fusion network (CFSFNet), in which the contributions of features are evaluated at the channel level for weighted fusion to enhance the discriminability of the features. The proposed CFSFNet consists of three main components including a feature extraction module (FEM), a feature selection module (FSM), and a channel-level feature fusion module (CFFM). Modality-shared and modality-specific features are first extracted by different multi-channel feature extractors in the FEM. The contributions of different features to identification are then evaluated at the channel level in the FSM. According to their contributions, modality-shared and modality-specific features are combined on selected high-response channels by a dual-channel-attention mean-weighted fusion in the CFFM. Through the collaboration between the CFFM and the FSM, the proposed method not only exploits both modality-shared properties and modality-specific characteristics but enhances the high discriminative features. Moreover, a novel tri-directional center triplet loss is proposed to combine with other loss constraints to guide the model to tighten the intra-class individuals and widen the inter-class gaps. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the superiority of the proposed method over state-of-the-art methods. Ablation studies also illustrate the effectiveness of each component of the proposed network. The source code of this work is publicly available at https://github.com/CV-ReID/CFSFNet.","manuscriptTitle":"Channel-level Feature Selection and Fusion Network for Visible-infrared Person Re-identification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-06 08:30:09","doi":"10.21203/rs.3.rs-7686860/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-08T23:56:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-03T09:18:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-26T09:16:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"250059926311477830801392445621847582326","date":"2025-11-19T02:53:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"198827362634198302406297089525568851589","date":"2025-11-19T02:27:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-16T11:40:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"76114813643653143257858995112898935302","date":"2025-11-05T02:46:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326122329542996918648286344840032246971","date":"2025-11-04T12:24:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-04T12:20:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-02T12:51:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-26T09:16:41+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-09-22T16:41:55+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":"4460b974-c022-4419-b295-f0bd4ec42898","owner":[],"postedDate":"November 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-09T16:11:14+00:00","versionOfRecord":{"articleIdentity":"rs-7686860","link":"https://doi.org/10.1007/s00530-025-02205-6","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2026-02-03 15:58:36","publishedOnDateReadable":"February 3rd, 2026"},"versionCreatedAt":"2025-11-06 08:30:09","video":"","vorDoi":"10.1007/s00530-025-02205-6","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02205-6","workflowStages":[]},"version":"v1","identity":"rs-7686860","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7686860","identity":"rs-7686860","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}