Decoding Cultural Heritage Values: A Deep Learning Framework for Recognition and Weighted Evaluation

Decoding Cultural Heritage Values: A Deep Learning Framework for Recognition and Weighted Evaluation | 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 Article Decoding Cultural Heritage Values: A Deep Learning Framework for Recognition and Weighted Evaluation Wenlun Xu, Bo Huang, Ying Tang, Chengyong Shi, Yifei Wang, Shuya Kong, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6446678/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Nov, 2025 Read the published version in npj Heritage Science → Version 1 posted 13 You are reading this latest preprint version Abstract Cultural heritage value serves as a critical foundation for guiding the protection and utilization of cultural heritage. However, existing methods for evaluating cultural heritage value face several inherent limitations, including evaluator subjectivity, high resource demands, and a lack of timely and objective evaluation capabilities. To overcome these challenges, we present the first application of deep learning to heritage value evaluation through our proposed Vision Transformer-based Heritage Value Evaluation model (ViT-HVE). This novel framework represents a breakthrough in automated cultural heritage analysis, enabling both visual recognition and quantitative evaluation of heritage values through an end-to-end deep learning approach. In this paper, the cultural heritage of the Yellow River in Shaanxi province is selected as a case study. A ten-dimensional value system characterizing these cultural heritage is extracted using the Latent Dirichlet Allocation (LDA) topic model. Based on this, we developed the first Cultural Heritage Value Recognition (CHVR) dataset in this domain. To facilitate the quantitative evaluation of cultural heritage values, we further introduce a Top-k Heritage Value Weighting (TK-HVW) method, which performs value weighting by extracting and normalizing the probability distributions over heritage value categories. To evaluate the effectiveness of the proposed method, we conduct a comparative analysis between ViT-HVE and five state-of-the-art deep learning models, and validate the accuracy of the model’s weighted outputs using expert evaluation. Furthermore, three distinct fine-tuning strategies are systematically investigated to enhance the performance of our model on the CHVR dataset. Experimental results indicate that ViT-HVE achieves the best performance in heritage value recognition tasks, and our proposed weighting method shows a high degree of consistency with expert evaluation results. The ViT-HVE evaluation method significantly enhances the objectivity and accuracy of cultural heritage recognition and evaluation, substantially reducing the cost and workload of related tasks, thereby offering scientific methodological support and practical guidance for the protection and utilization of cultural heritage. Cultural heritage Heritage value Value recognition and evaluation Vsion Transformer Deep Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 12 Nov, 2025 Read the published version in npj Heritage Science → Version 1 posted Editorial decision: Revision requested 23 Jun, 2025 Reviewers agreed at journal 16 Jun, 2025 Reviews received at journal 11 Jun, 2025 Reviews received at journal 18 May, 2025 Reviewers agreed at journal 05 May, 2025 Reviewers agreed at journal 04 May, 2025 Reviews received at journal 03 May, 2025 Reviewers agreed at journal 30 Apr, 2025 Reviewers agreed at journal 17 Apr, 2025 Reviewers invited by journal 16 Apr, 2025 Editor assigned by journal 14 Apr, 2025 Submission checks completed at journal 14 Apr, 2025 First submitted to journal 14 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-6446678","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":445357107,"identity":"a7851c2f-5eec-4f1e-ade0-5b19a4ae0c9f","order_by":0,"name":"Wenlun Xu","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Wenlun","middleName":"","lastName":"Xu","suffix":""},{"id":445357108,"identity":"929da4a9-30d6-4c6b-a3d8-57c8f2d09551","order_by":1,"name":"Bo Huang","email":"","orcid":"","institution":"Northwestern Polytechnical University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Huang","suffix":""},{"id":445357109,"identity":"f1d86a00-13bc-4cd5-8c83-99ac4369114a","order_by":2,"name":"Ying Tang","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Tang","suffix":""},{"id":445357110,"identity":"4943ce9f-7525-4fb7-92f1-be25ca785827","order_by":3,"name":"Chengyong Shi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYDACCcYGZjjnAxCzNwAJHmK1MM4AqT5AUAsDA1wLMw8xWuRnNzd+Lqi4Y7fheO/h17Y7DsvzSCQwPnjbxiBvjkOLwZ2DzdIzzjxL3nDmXJp17pnDhj0SCcyGc9sYDHc24NAikdjGzNt2ONngRo6ZcW7bbcb9Egls0rxtDAkGB3A4bAZIyz+oFsu22/ZAW9h/49PCcAOkpeGwHVCL8WPGttuJQC1szPi0GNxIbJbmOXY4QfLMGTPG3rb/yT08D5sl55yTMNyA02HpDz/z1By25zveY/zhZ1uabQ978sEPb8ps5HE6DAoSFxxgYJOAsBkbGMDxRQDYyzcwMH8gqGwUjIJRMApGJAAAbahgrpgP8XgAAAAASUVORK5CYII=","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":true,"prefix":"","firstName":"Chengyong","middleName":"","lastName":"Shi","suffix":""},{"id":445357111,"identity":"8259b9f9-742e-4f0f-a242-ef28a1581a91","order_by":4,"name":"Yifei Wang","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Yifei","middleName":"","lastName":"Wang","suffix":""},{"id":445357112,"identity":"89a0eab2-b421-45e0-8a81-190ecbb28a18","order_by":5,"name":"Shuya Kong","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Shuya","middleName":"","lastName":"Kong","suffix":""},{"id":445357113,"identity":"fa4f9a2f-5399-4dc2-92e7-2a1876c50053","order_by":6,"name":"Pengyue Yan","email":"","orcid":"","institution":"Northwest A\u0026F University","correspondingAuthor":false,"prefix":"","firstName":"Pengyue","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2025-04-14 13:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6446678/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6446678/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s40494-025-02143-6","type":"published","date":"2025-11-12T15:57:27+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96105639,"identity":"6a836be3-e53d-47f4-8a97-5aeb0c3fdf90","added_by":"auto","created_at":"2025-11-17 16:11:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":18143963,"visible":true,"origin":"","legend":"","description":"","filename":"submissionforDecodingCulturalHeritageValuesADeepLearningFrameworkforRecognitionandWeightedEvaluation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6446678/v1_covered_7a2e2da1-1b27-4d88-b291-07232552e1fe.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Decoding Cultural Heritage Values: A Deep Learning Framework for Recognition and Weighted Evaluation","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":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Cultural heritage, Heritage value, Value recognition and evaluation, Vsion Transformer, Deep Learning","lastPublishedDoi":"10.21203/rs.3.rs-6446678/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6446678/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Cultural heritage value serves as a critical foundation for guiding the protection and utilization of cultural heritage. However, existing methods for evaluating cultural heritage value face several inherent limitations, including evaluator subjectivity, high resource demands, and a lack of timely and objective evaluation capabilities. To overcome these challenges, we present the first application of deep learning to heritage value evaluation through our proposed Vision Transformer-based Heritage Value Evaluation model (ViT-HVE). This novel framework represents a breakthrough in automated cultural heritage analysis, enabling both visual recognition and quantitative evaluation of heritage values through an end-to-end deep learning approach. In this paper, the cultural heritage of the Yellow River in Shaanxi province is selected as a case study. A ten-dimensional value system characterizing these cultural heritage is extracted using the Latent Dirichlet Allocation (LDA) topic model. Based on this, we developed the first Cultural Heritage Value Recognition (CHVR) dataset in this domain. To facilitate the quantitative evaluation of cultural heritage values, we further introduce a Top-k Heritage Value Weighting (TK-HVW) method, which performs value weighting by extracting and normalizing the probability distributions over heritage value categories. To evaluate the effectiveness of the proposed method, we conduct a comparative analysis between ViT-HVE and five state-of-the-art deep learning models, and validate the accuracy of the model’s weighted outputs using expert evaluation. Furthermore, three distinct fine-tuning strategies are systematically investigated to enhance the performance of our model on the CHVR dataset. Experimental results indicate that ViT-HVE achieves the best performance in heritage value recognition tasks, and our proposed weighting method shows a high degree of consistency with expert evaluation results. The ViT-HVE evaluation method significantly enhances the objectivity and accuracy of cultural heritage recognition and evaluation, substantially reducing the cost and workload of related tasks, thereby offering scientific methodological support and practical guidance for the protection and utilization of cultural heritage.","manuscriptTitle":"Decoding Cultural Heritage Values: A Deep Learning Framework for Recognition and Weighted Evaluation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-07 06:51:43","doi":"10.21203/rs.3.rs-6446678/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-23T21:50:09+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"94848377078747884916639207375895194035","date":"2025-06-16T14:25:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-12T02:27:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-19T02:32:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"131961184510826615039060665913065115957","date":"2025-05-06T02:06:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"10597423553625023496749902063444224518","date":"2025-05-04T21:39:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-03T08:44:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"57852902093994447790033594938261717453","date":"2025-04-30T08:30:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"38626778473117196345213122328308661976","date":"2025-04-17T04:41:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-16T04:42:59+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-14T20:11:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-14T20:10:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj heritage science","date":"2025-04-14T13:49:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d63ba87d-b54f-49ad-8a08-af5df09e25f7","owner":[],"postedDate":"May 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-17T16:07:08+00:00","versionOfRecord":{"articleIdentity":"rs-6446678","link":"https://doi.org/10.1038/s40494-025-02143-6","journal":{"identity":"npj-heritage-science","isVorOnly":false,"title":"npj Heritage Science"},"publishedOn":"2025-11-12 15:57:27","publishedOnDateReadable":"November 12th, 2025"},"versionCreatedAt":"2025-05-07 06:51:43","video":"","vorDoi":"10.1038/s40494-025-02143-6","vorDoiUrl":"https://doi.org/10.1038/s40494-025-02143-6","workflowStages":[]},"version":"v1","identity":"rs-6446678","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6446678","identity":"rs-6446678","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}