Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence Recognition

Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence 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 Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence Recognition Suyuan Li, Xin Song This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2778719/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 Generally, a large amount of training data is essential to train deep learning model for obtaining more accurate detection performance in computer vision domain. However, to collect and annotate datasets will lead to extensive cost. In this letter, we propose a self-supervised auxiliary task to learn general videos features without adding any human-annotated labels, aiming at improving the performance of violence recognition. Firstly, we propose a violence recognition method based on convolutional neural network with self-supervised auxiliary task, which can learn visual feature for improving down-stream task (recognizing violence). Secondly, we establish a balance-weighting scheme to solve the crucial problem of balancing the self-supervised auxiliary task and violence recognition task. Thirdly, we develop an attention receptive-field module, indicating that the proper use of the spatial attention mechanism can effectively expand the receptive fields of the module, further improving semantically meaningful representation of the network. To evaluate the proposed method, two benchmark datasets have been used, and better performance is shown by the experimental results comparing with other state-of-the-art methods. Violence recognition attention module self-supervised learning CNN 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-2778719","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":189304997,"identity":"e6870b2b-336a-43b5-8e8c-2901590cdb62","order_by":0,"name":"Suyuan Li","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Suyuan","middleName":"","lastName":"Li","suffix":""},{"id":189304998,"identity":"d745e7ca-9e7c-45fc-961a-465fc88d8585","order_by":1,"name":"Xin Song","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYFACxgbmPxU2PPzsDVCBA0RoYeA5kyYj2QNTSlgLEPC2HbYxmJFApBb5GcltDyTOHOYxkHx78DFPGYMc340Exs8FeLQYnDnYbmBQkc5jLp2XbMxzjsFY8kYCs/QMfFrYG9skEs5Y81jOzjGT5m1jSNxwI4GNmQefw5oZ2yQOtjHzGNw8Y/4bqKWeoBaG441tko1tzjwGN3jMmIFaEgwIaQH6pU2a4Uwaj2RPjrHknHMShjPPPGyWxuuwGenPpBkqbOz52c8YfnhTZiPPdzz54Ge8DkMFbBIM4MglAbCRongUjIJRMApGCgAAnOxIXgs78UYAAAAASUVORK5CYII=","orcid":"","institution":"Northeastern University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Song","suffix":""}],"badges":[],"createdAt":"2023-04-05 02:14:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2778719/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2778719/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":36577722,"identity":"44fc4ee1-5cee-44a7-b90c-4a3df599b033","added_by":"auto","created_at":"2023-05-03 14:29:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":533951,"visible":true,"origin":"","legend":"","description":"","filename":"AttentionInspiringReceptiveFieldsMultiTaskNetworkviaSelfsupervisedLearningforViolenceRecognition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2778719/v1_covered_23e4298a-534d-480c-a946-c73c48e86dfc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence Recognition","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":"Violence recognition, attention module, self-supervised learning CNN","lastPublishedDoi":"10.21203/rs.3.rs-2778719/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2778719/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGenerally, a large amount of training data is essential to train deep learning model for obtaining more accurate detection performance in computer vision domain. However, to collect and annotate datasets will lead to extensive cost. In this letter, we propose a self-supervised auxiliary task to learn general videos features without adding any human-annotated labels, aiming at improving the performance of violence recognition. Firstly, we propose a violence recognition method based on convolutional neural network with self-supervised auxiliary task, which can learn visual feature for improving down-stream task (recognizing violence). Secondly, we establish a balance-weighting scheme to solve the crucial problem of balancing the self-supervised auxiliary task and violence recognition task. Thirdly, we develop an attention receptive-field module, indicating that the proper use of the spatial attention mechanism can effectively expand the receptive fields of the module, further improving semantically meaningful representation of the network. To evaluate the proposed method, two benchmark datasets have been used, and better performance is shown by the experimental results comparing with other state-of-the-art methods.\u003c/p\u003e","manuscriptTitle":"Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-04-06 12:31:12","doi":"10.21203/rs.3.rs-2778719/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":"c294bd8c-e46a-46ea-aedc-7b7460e0065b","owner":[],"postedDate":"April 6th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2023-05-03T14:29:33+00:00","versionOfRecord":[],"versionCreatedAt":"2023-04-06 12:31:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2778719","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2778719","identity":"rs-2778719","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}