AQ-CSL: Attention Querying Facial Action Unit Detection Net withCross Subject Learning

AQ-CSL: Attention Querying Facial Action Unit Detection Net withCross Subject Learning | 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 AQ-CSL: Attention Querying Facial Action Unit Detection Net withCross Subject Learning Wangding Zeng, Yuanpeng Ji, Donghao Chen, Honggang Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4484075/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 5 You are reading this latest preprint version Abstract Recently, the advancement of deep learning has led to considerable breakthroughs in the automated detection of ActionUnits (AUs). Nevertheless, this field is still faced with various challenges, including limited subjects in shared datasetsand the difficulty of collecting AU data as domain knowledge required for annotating AUs. These issues make it arduousfor the model to generalize across different subjects and attain satisfactory performance on all AUs. To address thesechallenges, we propose two methods, namely AU-specific Querying (AQ) and Feedback Querying (FQ). AQ learns theglobal semantics of a particular AU, while FQ provides local structure information related to the AU semantic vector.The combination of these two operations enables the model to leverage both local features and global semantics of AUs.Moreover, Feedback Querying exhibits strong extensibility, which has led us to propose Cross-subject Querying (CQ).This method learns a subject-independent feature representation for each AU, resulting in improved generalizationability across different subjects. We demonstrate the effectiveness of our methods through visual presentations andablation analysis. By combining all the strategies, our proposed AQ-CSL becomes the state-of-the-art model on theDISFA and BP4D datasets. Image classification Facial expression detection Deep learning Facial action units Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 13 Aug, 2024 Reviewers invited by journal 05 Jun, 2024 Editor assigned by journal 30 May, 2024 Submission checks completed at journal 30 May, 2024 First submitted to journal 27 May, 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-4484075","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":312792437,"identity":"cc48d6e6-8129-4f0b-918c-b6a9a9a5f6d0","order_by":0,"name":"Wangding Zeng","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Wangding","middleName":"","lastName":"Zeng","suffix":""},{"id":312792438,"identity":"20dcdd76-2b10-4414-8b34-d01df98746a8","order_by":1,"name":"Yuanpeng Ji","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Yuanpeng","middleName":"","lastName":"Ji","suffix":""},{"id":312792439,"identity":"ab5fcfd9-ca8a-4c2c-8326-ee90241cf206","order_by":2,"name":"Donghao Chen","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Donghao","middleName":"","lastName":"Chen","suffix":""},{"id":312792440,"identity":"844d65c7-6b74-4273-a5ea-81b5d93d9ee5","order_by":3,"name":"Honggang Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYDACCR4Gho8NUDbRWhhnArXwkKSFmZckLfKzew+/tt1xOM+egfngbR4GuzyCWhjnnEuzzj1zuJiHgS3ZmochuZigFmaJHDPj3LbDiT0MPGbSPAwHEhsIaWEDabEEa+H/RpwWHokc48eMEFvYiNMiAbSFsfdMejHPYTZjyzkGyYS1yM/IMf7wc4d1Hnt788MbbyrsCGsBewdIJDAwg9gGRKgHAuYPYC2jYBSMglEwCnABAKX+NXF0qr9FAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Honggang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-05-27 10:03:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4484075/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4484075/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04627-1","type":"published","date":"2025-09-22T15:58:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92430653,"identity":"5e807511-e5d2-4c7d-a1d8-e17353b68a01","added_by":"auto","created_at":"2025-09-29 16:07:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1443604,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate12.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4484075/v1_covered_c3f80345-ddef-4945-bf19-36f106dbadc0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AQ-CSL: Attention Querying Facial Action Unit Detection Net withCross Subject Learning","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":"Image classification, Facial expression detection, Deep learning, Facial action units","lastPublishedDoi":"10.21203/rs.3.rs-4484075/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4484075/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Recently, the advancement of deep learning has led to considerable breakthroughs in the automated detection of ActionUnits (AUs). Nevertheless, this field is still faced with various challenges, including limited subjects in shared datasetsand the difficulty of collecting AU data as domain knowledge required for annotating AUs. These issues make it arduousfor the model to generalize across different subjects and attain satisfactory performance on all AUs. To address thesechallenges, we propose two methods, namely AU-specific Querying (AQ) and Feedback Querying (FQ). AQ learns theglobal semantics of a particular AU, while FQ provides local structure information related to the AU semantic vector.The combination of these two operations enables the model to leverage both local features and global semantics of AUs.Moreover, Feedback Querying exhibits strong extensibility, which has led us to propose Cross-subject Querying (CQ).This method learns a subject-independent feature representation for each AU, resulting in improved generalizationability across different subjects. We demonstrate the effectiveness of our methods through visual presentations andablation analysis. By combining all the strategies, our proposed AQ-CSL becomes the state-of-the-art model on theDISFA and BP4D datasets.","manuscriptTitle":"AQ-CSL: Attention Querying Facial Action Unit Detection Net withCross Subject Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-12 06:53:13","doi":"10.21203/rs.3.rs-4484075/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-13T20:17:49+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-05T17:46:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-30T14:31:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-30T14:31:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-05-27T10:01:59+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":"06cfe9c6-7348-4bb3-a3e1-c873b814c3fb","owner":[],"postedDate":"June 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-29T16:04:32+00:00","versionOfRecord":{"articleIdentity":"rs-4484075","link":"https://doi.org/10.1007/s11760-025-04627-1","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-09-22 15:58:12","publishedOnDateReadable":"September 22nd, 2025"},"versionCreatedAt":"2024-06-12 06:53:13","video":"","vorDoi":"10.1007/s11760-025-04627-1","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04627-1","workflowStages":[]},"version":"v1","identity":"rs-4484075","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4484075","identity":"rs-4484075","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}