Pose Scoring Model for Refining Multi-Person Poses

Pose Scoring Model for Refining Multi-Person Poses | 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 Pose Scoring Model for Refining Multi-Person Poses Zeinab Ghasemi-Naraghi, Ahmad Nickabadi, Reza Safabakhsh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5054149/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract In multi-person pose estimation, the coordinates of body joints are estimated to predict the body poses of several people in an image. Although significant progress has been made in this area in recent years, the solutions still suffer from certain weaknesses. One weakness is the detection of a larger number of poses than the actual number of human instances in the image. To face this problem, the final poses are often selected by thresholding the detected human scores. This, however, is not optimal because a pose with a lower priority may be assigned a higher score and selected as the final pose. In this paper, we introduce a problem, explain the reason, and present a pose scoring model as a solution. This model predicts the confidence score for the pose based on the human image, the location and the confidence score of the joints and the structure between the joints of the body. We formulate the problem using Conditional Random Fields and introduce suitable potential functions. To infer the best pose score, we design a neural network whose inputs are a human image and an initial pose. To train the model, a lot of training data and corresponding labels should be provided. For this purpose, we introduce Monte Carlo and GAN-based data augmentation methods, and a scoring function to train the model. Also, we investigate the effect of the pose scores on the reliability and accuracy of multi-person pose estimation models. The proposed idea is implemented as a deep neural network and can be easily applied to other multi-person pose estimation models as a model-agnostic method. In addition to the usual pose estimation evaluation metrics, we consider the number of poses to compare the models in terms of reliability. Experiments show that the performance of the proposed model is higher than the state-of-the-art models. Conducting further research can help to simplify and reduce the complexity of the model. Pose Scoring Model Multi-Person Pose Estimation Human Pose Refiner Conditional Random Fields Model-Agnostic Method Full Text Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 21 Jan, 2025 Reviewers invited by journal 21 Jan, 2025 First submitted to journal 12 Sep, 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-5054149","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":405040868,"identity":"4dbfe0f4-f090-4f69-b1b0-8ab11089f3f4","order_by":0,"name":"Zeinab Ghasemi-Naraghi","email":"","orcid":"","institution":"Amirkabir University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zeinab","middleName":"","lastName":"Ghasemi-Naraghi","suffix":""},{"id":405040869,"identity":"2bd82680-2b3d-45b0-ab0c-cbe036e5e3fe","order_by":1,"name":"Ahmad Nickabadi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYDACZiBkbGBgbGNvgIsQq4XnAAPDAaK0MEC1NEgkQLUQAubszI8Nfu6wk+2TfPxM+gODnTwDO+8DvFosm9mME3vPJBu3SaeZSRxgSDZsYGY3wKvF4DAP8wHeNubENukEkBbmBAZmNvwOA2k5+LetPrFN8vg3oJZ64rQk87YdTmyT4AHZcpgYLWzGxrJnjhu38eQUW5wxOG7YRlDL+cOPJd/uqJad3358442Kimp5fv5j+LWgm8DAQMCOUTAKRsEoGAXEAABzTztAW6+24gAAAABJRU5ErkJggg==","orcid":"","institution":"Amirkabir University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Ahmad","middleName":"","lastName":"Nickabadi","suffix":""},{"id":405040870,"identity":"9af324c5-e224-44d4-9d1a-a4749376845b","order_by":2,"name":"Reza Safabakhsh","email":"","orcid":"","institution":"Amirkabir University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Reza","middleName":"","lastName":"Safabakhsh","suffix":""}],"badges":[],"createdAt":"2024-09-08 21:03:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5054149/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5054149/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":74509934,"identity":"dffab691-43e7-48c5-a15f-52e57c0038b6","added_by":"auto","created_at":"2025-01-23 03:32:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":710751,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5054149/v1_covered_de7ba10e-5b60-402d-9c4a-eebaf00257af.pdf"}],"financialInterests":"","formattedTitle":"Pose Scoring Model for Refining Multi-Person Poses","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Pose Scoring Model, Multi-Person Pose Estimation, Human Pose Refiner, Conditional Random Fields, Model-Agnostic Method","lastPublishedDoi":"10.21203/rs.3.rs-5054149/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5054149/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In multi-person pose estimation, the coordinates of body joints are estimated to predict the body poses of several people in an image. Although significant progress has been made in this area in recent years, the solutions still suffer from certain weaknesses. One weakness is the detection of a larger number of poses than the actual number of human instances in the image. To face this problem, the final poses are often selected by thresholding the detected human scores. This, however, is not optimal because a pose with a lower priority may be assigned a higher score and selected as the final pose. In this paper, we introduce a problem, explain the reason, and present a pose scoring model as a solution. This model predicts the confidence score for the pose based on the human image, the location and the confidence score of the joints and the structure between the joints of the body. We formulate the problem using Conditional Random Fields and introduce suitable potential functions. To infer the best pose score, we design a neural network whose inputs are a human image and an initial pose. To train the model, a lot of training data and corresponding labels should be provided. For this purpose, we introduce Monte Carlo and GAN-based data augmentation methods, and a scoring function to train the model. Also, we investigate the effect of the pose scores on the reliability and accuracy of multi-person pose estimation models. The proposed idea is implemented as a deep neural network and can be easily applied to other multi-person pose estimation models as a model-agnostic method. In addition to the usual pose estimation evaluation metrics, we consider the number of poses to compare the models in terms of reliability. Experiments show that the performance of the proposed model is higher than the state-of-the-art models. Conducting further research can help to simplify and reduce the complexity of the model.","manuscriptTitle":"Pose Scoring Model for Refining Multi-Person Poses","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-23 03:16:04","doi":"10.21203/rs.3.rs-5054149/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-01-21T21:07:07+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-01-21T10:36:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2024-09-12T15:19:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a34e56d2-d9fb-4df1-830f-0cf443639d71","owner":[],"postedDate":"January 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-01-23T03:16:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-23 03:16:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5054149","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5054149","identity":"rs-5054149","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}