{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:28:30Z","timestamp":1781598510025,"version":"3.54.5"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T00:00:00Z","timestamp":1708646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Cult. Herit."],"published-print":{"date-parts":[[2024,2,29]]},"abstract":"<jats:p>The cultural heritage buildings (CHB), which are part of mankind\u2019s history and identity, are in constant danger of damage, or in extreme cases, complete destruction. Thus, it\u2019s of utmost importance to preserve them by identifying the existent, or presumptive, defects using novel methods so that renovation processes can be done in a timely manner and with higher accuracy. The main goal of this research is to use new Deep Learning (DL) methods in the process of preserving CHBs (situated in Iran); a goal that has been neglected especially in developing countries such as Iran, as these countries still preserve their CHBs using manual, and even archaic, methods that need direct human supervision. Having proven their effectiveness and performance when it comes to processing images, the Convolutional Neural Networks (CNNs) are a staple in computer vision (CV) literacy and this article is not exempt. When lacking enough CHB images, training a CNN from scratch would be very difficult and prone to overfitting; that\u2019s why we opted to use a technique called transfer learning (TL) in which we used pre-trained ResNet, MobileNet, and Inception networks, for classification. Even more, the Grad-CAM was utilized to localize the defects to some extent. The final results were very favorable, compared to similar articles. We reached 94% in Precision, Recall, and F1-Score with our fine-tuned MobileNetV2 model, which showed a 4%\u20135% improvement over other similar works. The final proposed model can pave the way for moving from manual to unmanned CHB conservation, hence an increase in accuracy and a decrease in human-induced errors.<\/jats:p>","DOI":"10.1145\/3631130","type":"journal-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T21:56:24Z","timestamp":1698702984000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Deep Learning for Identifying Iran\u2019s Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3320-2667","authenticated-orcid":false,"given":"Mahdi","family":"Bahrami","sequence":"first","affiliation":[{"name":"IT Department, Tarbiat Modares University (TMU), Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7758-9920","authenticated-orcid":false,"given":"Amir","family":"Albadvi","sequence":"additional","affiliation":[{"name":"IT Department, Tarbiat Modares University (TMU), Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,23]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra James","year":"2012","unstructured":"James Bergstra andYoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13(22012), 281\u2013305.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-097086-8.12185-3"},{"key":"e_1_3_2_4_2","unstructured":"UNESCO World Heritage Centre. 2022. Iran (Islamic Republic of) Heritage Sites. https:\/\/whc.unesco.org\/en\/statesparties\/IR\/"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/robot.1991.132043"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1205.2653"},{"key":"e_1_3_2_7_2","article-title":"Computer vision for behaviour-based safety inconstruction: A review and future directions","volume":"43","author":"Fang Weili","year":"2020","unstructured":"Weili Fang, Peter EDLove, Hanbin Luo, and Lieyun Ding. 2020. Computer vision for behaviour-based safety inconstruction: A review and future directions. Advanced Engineering Informatics 43 (2020), 100980.","journal-title":"Advanced Engineering Informatics"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.017"},{"key":"e_1_3_2_9_2","volume-title":"Deep Learning","author":"Goodfellow Ian","year":"2016","unstructured":"Ian Goodfellow, YoshuaBengio, and Aaron Courville. 2016. Deep Learning.MIT Press."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu Jiuxiang","year":"2018","unstructured":"Jiuxiang Gu, ZhenhuaWang, Jason Kuen, Lianyang Ma,Amir Shahroudy, Bing Shuai,Ting Liu, Xingxing Wang,Gang Wang, Jianfei Cai, et\u00a0al. 2018. Recent advances in convolutional neural networks. Pattern Recognition 77(2018), 354\u2013377.","journal-title":"Pattern Recognition"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1512.03385"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Kaiming He XiangyuZhang Shaoqing Ren and Jian Sun. 2016. Identity mappings in deep residual networks. (32016). 10.48550\/arxiv.1603.05027","DOI":"10.48550\/arxiv.1603.05027"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3846\/20297955.2015.1088415"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Geoffrey E. Hinton NitishSrivastava Alex Krizhevsky IlyaSutskever and Ruslan R. Salakhutdinov. 2012. Improving neural networks by preventingco-adaptation of feature detectors. (2012). DOI:10.48550\/arxiv.1207.0580","DOI":"10.48550\/arxiv.1207.0580"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Andrew G. Howard MenglongZhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networksfor mobile vision applications. (2017). DOI:10.48550\/arxiv.1704.04861","DOI":"10.48550\/arxiv.1704.04861"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1502.03167"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/NECO.1989.1.4.541"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/app7100992"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/mti2020021"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.GLTP.2022.04.020"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOTEH.2019.8717658"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0B013E3181EC173D"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20102915"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.CULHER.2021.01.002"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1002\/stc.2751"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/s19163556"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1801.04381"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_29_2","volume-title":"Digital Imaging for Cultural HeritagePreservation: Analysis, Restoration, and Reconstruction of AncientArtworks","author":"Stanco Filippo","year":"2011","unstructured":"Filippo Stanco, Sebastiano Battiato, and Giovani Gallo. 2011. Digital Imaging for Cultural HeritagePreservation: Analysis, Restoration, and Reconstruction of AncientArtworks. Retrieved from https:\/\/books.google.com\/books?id=QHnBxQ2xhGQC&pgis=1"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1602.07261"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1409.4842"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.culher.2010.01.006"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.03.003"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12488"},{"key":"e_1_3_2_35_2","first-page":"2921","article-title":"Learning deep features for discriminativelocalization","author":"Zhou Bolei","year":"2015","unstructured":"Bolei Zhou, AdityaKhosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2015. Learning deep features for discriminativelocalization. Proceedings of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition .12 (2015), 2921\u20132929. arXiv:1512.04150. Retrieved from http:\/\/arxiv.org\/abs\/1512.04150","journal-title":"Proceedings of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1911.02685"},{"key":"e_1_3_2_37_2","unstructured":"Zidea. 2021. Introduce the MobileNet Network Structure and its Depthwise Separable Convolution. Retrieved from https:\/\/www.bilibili.com\/video\/BV1944y1h7yY\/?spm_id_from=333.337.search-card.all.click"}],"container-title":["Journal on Computing and Cultural Heritage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631130","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:35:51Z","timestamp":1750178151000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,23]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2,29]]}},"alternative-id":["10.1145\/3631130"],"URL":"https:\/\/doi.org\/10.1145\/3631130","relation":{},"ISSN":["1556-4673","1556-4711"],"issn-type":[{"value":"1556-4673","type":"print"},{"value":"1556-4711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,23]]},"assertion":[{"value":"2023-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-18","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}