Attribute correlation mask fusion network for pedestrian attribute recognition

Attribute correlation mask fusion network for pedestrian attribute 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 Attribute correlation mask fusion network for pedestrian attribute recognition Baoan Li, Long Zhang, Shangzhi Teng, Xueqiang LYU This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4292609/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Oct, 2024 Read the published version in The Visual Computer → Version 1 posted 9 You are reading this latest preprint version Abstract The main goal of Pedestrian Attribute Recognition (PAR) is to identify various attributes of pedestrians captured in video surveillance. Due to the numerous categories of pedestrian attribute labels, the complex and easily overlooked correlations among attributes, PAR is a challenging task. Traditional methods usually treat each attribute independently, ignoring the possible intrinsic correlations between attributes.We design a pedestrian attribute recognition network ACMFNet which can fuse pedestrian attributes uniqueness features and attribute correlation features. Specifically, we propose an attribute correlation query module (ACQM), which are used to learn discriminative attribute features. Then, we construct a mask fusion module (MFM) to automatically learn the importance of the image feature and attribute correlation feature. To better distinguish the modality differences between images and attribute texts, we propose modality prompt. Experimental results show that our method can significantly enhance the network’s ability to recognize pedestrian attributes. On three pedestrian attribute recognition datasets PA100K, PETA, and UAV-Human, our proposed method shows competitive performance compared to the state-of-the-art methods. Our source code is available at \url{ https://github.com/luffy-op/ACMFNet . Pedestrian Attribute Recognition Modality Fusion Mask Fusion Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Oct, 2024 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 06 Jul, 2024 Reviews received at journal 19 Jun, 2024 Reviews received at journal 14 Jun, 2024 Reviewers agreed at journal 17 May, 2024 Reviewers agreed at journal 16 May, 2024 Reviewers invited by journal 16 May, 2024 Editor assigned by journal 20 Apr, 2024 Submission checks completed at journal 20 Apr, 2024 First submitted to journal 19 Apr, 2024 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-4292609","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":294169046,"identity":"db64cd81-66eb-46bb-a619-819be24ba48a","order_by":0,"name":"Baoan Li","email":"","orcid":"","institution":"Beijing Information Science \u0026 Technology University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Baoan","middleName":"","lastName":"Li","suffix":""},{"id":294169049,"identity":"a1a5cfbb-f05c-485b-bbd5-e17c7e086a7c","order_by":1,"name":"Long Zhang","email":"","orcid":"","institution":"Beijing Information Science \u0026 Technology University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Long","middleName":"","lastName":"Zhang","suffix":""},{"id":294169051,"identity":"7c70c5bc-1636-42e5-bf00-4835739f351f","order_by":2,"name":"Shangzhi Teng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIiWNgGAWjYLACxgYQycNw4GODBESEB49qHmQtB2cCtfCQpIWZt4GBsBZ79t7DL3/usMuT9z978LDtDgt7e4kExgdv2xjkzXHZwnMuzZr3THKx4YFzCYdzz0gk9kgkMBvObWMw3NmAQ4tEjpkxYxtz4sbGHoPDuW0SCTwSCWzSvG0MCQYHcGiRf2Nm+LOtPnFjM4/BYcs2CXugFvbfeLVI8Bg/4G07nDifDaiFsU2CEegwNma8Ws7kmAEVHE/cwMNjcLAX5JczD5sl55yTMNyAQwt7+xnjjz/bqhPn958x/vBzR509e3vywQ9vymzkcdkCBGzgGEdSAI4mCZzqgYD5A4iUb8CnZhSMglEwCkY0AABDz1mqtOqnKAAAAABJRU5ErkJggg==","orcid":"","institution":"Beijing Information Science \u0026 Technology University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Shangzhi","middleName":"","lastName":"Teng","suffix":""},{"id":294169053,"identity":"d123190b-cc1c-432e-a65b-c32e00f2ef06","order_by":3,"name":"Xueqiang LYU","email":"","orcid":"","institution":"Beijing Information Science \u0026 Technology University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xueqiang","middleName":"","lastName":"LYU","suffix":""}],"badges":[],"createdAt":"2024-04-19 10:32:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4292609/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4292609/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-024-03629-3","type":"published","date":"2024-10-16T15:58:14+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":67149124,"identity":"5c096459-7216-48b6-b9a5-e5afea6ae397","added_by":"auto","created_at":"2024-10-21 16:12:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":757313,"visible":true,"origin":"","legend":"","description":"","filename":"nsbrstfkysmrcxxnnfhcxqggyzgyhkkn.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4292609/v1_covered_e049b33e-18c5-473b-bd94-01e0bbb944c9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Attribute correlation mask fusion network for pedestrian attribute 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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Pedestrian Attribute Recognition, Modality Fusion, Mask Fusion","lastPublishedDoi":"10.21203/rs.3.rs-4292609/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4292609/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The main goal of Pedestrian Attribute Recognition (PAR) is to identify various attributes of pedestrians captured in video surveillance. Due to the numerous categories of pedestrian attribute labels, the complex and easily overlooked correlations among attributes, PAR is a challenging task. Traditional methods usually treat each attribute independently, ignoring the possible intrinsic correlations between attributes.We design a pedestrian attribute recognition network ACMFNet which can fuse pedestrian attributes uniqueness features and attribute correlation features. Specifically, we propose an attribute correlation query module (ACQM), which are used to learn discriminative attribute features. Then, we construct a mask fusion module (MFM) to automatically learn the importance of the image feature and attribute correlation feature. To better distinguish the modality differences between images and attribute texts, we propose modality prompt. Experimental results show that our method can significantly enhance the network’s ability to recognize pedestrian attributes. On three pedestrian attribute recognition datasets PA100K, PETA, and UAV-Human, our proposed method shows competitive performance compared to the state-of-the-art methods. Our source code is available at \\url{https://github.com/luffy-op/ACMFNet.","manuscriptTitle":"Attribute correlation mask fusion network for pedestrian attribute recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-24 06:48:04","doi":"10.21203/rs.3.rs-4292609/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-07-06T10:37:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-19T05:44:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-14T09:23:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"188835491083780487216306278344187816890","date":"2024-05-17T05:19:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"127078487440324829176752911775360832604","date":"2024-05-17T03:40:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-17T02:31:07+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-20T14:06:24+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-20T10:11:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2024-04-19T10:31:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"927c1ff0-36d2-432c-8a24-006fa69c049e","owner":[],"postedDate":"April 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-10-21T16:05:51+00:00","versionOfRecord":{"articleIdentity":"rs-4292609","link":"https://doi.org/10.1007/s00371-024-03629-3","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2024-10-16 15:58:14","publishedOnDateReadable":"October 16th, 2024"},"versionCreatedAt":"2024-04-24 06:48:04","video":"","vorDoi":"10.1007/s00371-024-03629-3","vorDoiUrl":"https://doi.org/10.1007/s00371-024-03629-3","workflowStages":[]},"version":"v1","identity":"rs-4292609","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4292609","identity":"rs-4292609","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}