Facial Emotion Recognition Based on ResNet18 with Multi-Dimensional Attention Mechanisms

Facial Emotion Recognition Based on ResNet18 with Multi-Dimensional Attention Mechanisms | 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 Facial Emotion Recognition Based on ResNet18 with Multi-Dimensional Attention Mechanisms 阳 西, 陈雪 吴, 天宇 孟, 昆珍 李 This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6385083/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Oct, 2025 Read the published version in Memetic Computing → Version 1 posted 13 You are reading this latest preprint version Abstract Emotion, as a fundamental characteristic of humans, is the most important non-verbal way of expressing inner feelings and intentions, playing a crucial role in communication. Although various deep learning frameworks have been applied to the field of emotion recognition, facial images contain rich emotional features in the eyebrows, mouth corners, eyes, as well as changes in skin tone, light-shadow contrast, and muscle tension distribution. How to effectively characterize these emotional features from multiple dimensions remains a significant challenge in facial emotion recognition. This study proposes an enhanced ResNet18 architecture incorporating three specialized attention mechanisms: (1) channel-wise attention for feature refinement, (2) spatial attention for regional emphasis, and (3) multi-scale attention for hierarchical feature fusion. This synergistic design enables comprehensive integration of features across global contexts, local details, and varying granularities, significantly improving facial emotion recognition accuracy. Our model was evaluated on the DEAP dataset for classification experiments based on arousal and valence. The binary classification accuracy for valence and arousal reached 99.21% and 99.20%, respectively, while the accuracy for four-class emotion recognition was 97.45%. Experimental results demonstrate that our proposed method can effectively extract multi-dimensional features from facial expressions and improve the accuracy and robustness of emotion recognition. Our approach provides innovative feature extraction techniques and a theoretical foundation for emotion recognition based on facial images, offering significant reference value for enhancing recognition accuracy. facial emotion recognition ResNet18 channel attention mechanism spatial attention mechanism multi-scale attention mechanism Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Oct, 2025 Read the published version in Memetic Computing → Version 1 posted Editorial decision: Revision requested 06 Jun, 2025 Reviews received at journal 02 Jun, 2025 Reviews received at journal 14 May, 2025 Reviews received at journal 11 May, 2025 Reviews received at journal 11 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers invited by journal 06 May, 2025 Editor assigned by journal 22 Apr, 2025 Submission checks completed at journal 07 Apr, 2025 First submitted to journal 06 Apr, 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-6385083","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452981305,"identity":"90c6768d-dd17-4149-adac-3e3ca5df4472","order_by":0,"name":"阳 西","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIiWNgGAWjYBACxvkPEgw+/qmR42dvIFILc0PCg8KZDceMJXsOEKmFvSHxwWfOBuZEgxsJRGrhbTicuJlxB1uCwc3HG28w1NhEE9Qi2diWbFx4RiZP8nZasQXDsbTcBkJaDJt50oxnsLEV893OMZNgbDhMWIv9Mf7vv3nYmBMbbp4hUgtjD0OCMW8bc+KEGzzEapnBkGA44wwokIF+SSDGLyAtBh8qQFF5eOONDzU2hLUgAwOJBFKUQ7SQqmMUjIJRMApGBgAA9udExRGzhjgAAAAASUVORK5CYII=","orcid":"","institution":"Northeast Electric Power University","correspondingAuthor":true,"prefix":"","firstName":"阳","middleName":"","lastName":"西","suffix":""},{"id":452981306,"identity":"60d806f3-7319-4643-ab3a-f24f13254d52","order_by":1,"name":"陈雪 吴","email":"","orcid":"","institution":"Northeast Electric Power University","correspondingAuthor":false,"prefix":"","firstName":"陈雪","middleName":"","lastName":"吴","suffix":""},{"id":452981307,"identity":"855c14ff-ffd7-4569-8805-01797fd098fd","order_by":2,"name":"天宇 孟","email":"","orcid":"","institution":"Changchun University of Technology","correspondingAuthor":false,"prefix":"","firstName":"天宇","middleName":"","lastName":"孟","suffix":""},{"id":452981308,"identity":"5b9214e6-e7b3-4e92-acb1-8455e68f13a6","order_by":3,"name":"昆珍 李","email":"","orcid":"","institution":"Northeast Electric Power University","correspondingAuthor":false,"prefix":"","firstName":"昆珍","middleName":"","lastName":"李","suffix":""}],"badges":[],"createdAt":"2025-04-06 06:38:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6385083/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6385083/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s12293-025-00476-0","type":"published","date":"2025-10-23T16:16:25+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94490283,"identity":"55da29d5-10db-45f8-b6ce-c65247227c75","added_by":"auto","created_at":"2025-10-27 17:08:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1123663,"visible":true,"origin":"","legend":"","description":"","filename":"Facialemotionrecognization.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6385083/v1_covered_d2c78640-5ab5-41bd-b9db-789bbac1946d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Facial Emotion Recognition Based on ResNet18 with Multi-Dimensional Attention Mechanisms","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":"memetic-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"meme","sideBox":"Learn more about [Memetic Computing](http://link.springer.com/journal/12289)","snPcode":"12293","submissionUrl":"https://submission.nature.com/new-submission/12293/3","title":"Memetic Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"facial emotion recognition, ResNet18, channel attention mechanism, spatial attention mechanism, multi-scale attention mechanism","lastPublishedDoi":"10.21203/rs.3.rs-6385083/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6385083/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e Emotion, as a fundamental characteristic of humans, is the most important non-verbal way of expressing inner feelings and intentions, playing a crucial role in communication. Although various deep learning frameworks have been applied to the field of emotion recognition, facial images contain rich emotional features in the eyebrows, mouth corners, eyes, as well as changes in skin tone, light-shadow contrast, and muscle tension distribution. How to effectively characterize these emotional features from multiple dimensions remains a significant challenge in facial emotion recognition. This study proposes an enhanced ResNet18 architecture incorporating three specialized attention mechanisms: (1) channel-wise attention for feature refinement, (2) spatial attention for regional emphasis, and (3) multi-scale attention for hierarchical feature fusion. This synergistic design enables comprehensive integration of features across global contexts, local details, and varying granularities, significantly improving facial emotion recognition accuracy. Our model was evaluated on the DEAP dataset for classification experiments based on arousal and valence. The binary classification accuracy for valence and arousal reached 99.21% and 99.20%, respectively, while the accuracy for four-class emotion recognition was 97.45%. Experimental results demonstrate that our proposed method can effectively extract multi-dimensional features from facial expressions and improve the accuracy and robustness of emotion recognition. Our approach provides innovative feature extraction techniques and a theoretical foundation for emotion recognition based on facial images, offering significant reference value for enhancing recognition accuracy.\u003c/p\u003e","manuscriptTitle":"Facial Emotion Recognition Based on ResNet18 with Multi-Dimensional Attention Mechanisms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-08 17:39:55","doi":"10.21203/rs.3.rs-6385083/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-06T04:16:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-02T09:47:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-15T02:48:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-11T12:53:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-11T10:12:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301339755908050892537593524348196585529","date":"2025-05-07T03:51:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319122245859717385755367087369750857639","date":"2025-05-06T08:52:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"106384224463081292655752504760496563777","date":"2025-05-06T07:25:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"104102751284875302271300828423233377229","date":"2025-05-06T05:52:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-06T05:24:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-22T09:36:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-07T10:31:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Memetic Computing","date":"2025-04-06T06:22:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"memetic-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"meme","sideBox":"Learn more about [Memetic Computing](http://link.springer.com/journal/12289)","snPcode":"12293","submissionUrl":"https://submission.nature.com/new-submission/12293/3","title":"Memetic Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"27a91999-e981-4038-b010-600a749fb0cd","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-27T16:25:33+00:00","versionOfRecord":{"articleIdentity":"rs-6385083","link":"https://doi.org/10.1007/s12293-025-00476-0","journal":{"identity":"memetic-computing","isVorOnly":false,"title":"Memetic Computing"},"publishedOn":"2025-10-23 16:16:25","publishedOnDateReadable":"October 23rd, 2025"},"versionCreatedAt":"2025-05-08 17:39:55","video":"","vorDoi":"10.1007/s12293-025-00476-0","vorDoiUrl":"https://doi.org/10.1007/s12293-025-00476-0","workflowStages":[]},"version":"v1","identity":"rs-6385083","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6385083","identity":"rs-6385083","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}