{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:43:14Z","timestamp":1766306594766,"version":"3.48.0"},"reference-count":22,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":265,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1016\/j.procs.2025.09.324","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T22:14:26Z","timestamp":1762467266000},"page":"2036-2046","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hybrid Transformer-Based Framework for Building Detection in High-Resolution Satellite Imagery: Integrating SAM, PVT, and Mask2Former"],"prefix":"10.1016","volume":"270","author":[{"given":"Ezil Sam","family":"Leni A","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Revathi","family":"T","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niranchana","family":"R","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2025.09.324_bib1","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al. (2022). Masked-Attention Mask Transformer for Universal Image Segmentation. European Conference on Computer Vision (ECCV).","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.procs.2025.09.324_bib2","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al. (2021). Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. IEEE\/CVF International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.procs.2025.09.324_bib3","unstructured":"Kirillov, A., et al. (2023). Segment Anything. arXiv preprint arXiv:2304.02643."},{"issue":"2","key":"10.1016\/j.procs.2025.09.324_bib4","first-page":"602","article-title":"Transformer-based Semantic Segmentation for Large-Scale Building Footprint Extraction from Very-High-Resolution Satellite Images","volume":"73","author":"Gibril","year":"2024","journal-title":"Advances in Space Research"},{"key":"10.1016\/j.procs.2025.09.324_bib5","doi-asserted-by":"crossref","unstructured":"Teo, T.-A., & Chen, P.-C. (2025). Building Change Detection in Aerial Imagery Using End-to-End Deep Learning Semantic Segmentation Techniques. Buildings.","DOI":"10.3390\/buildings15050695"},{"issue":"6","key":"10.1016\/j.procs.2025.09.324_bib6","first-page":"e0299732","article-title":"STransU2Net: Transformer-Based Hybrid Model for Building Segmentation in Satellite Images","volume":"19","year":"2024","journal-title":"PLOS ONE"},{"key":"10.1016\/j.procs.2025.09.324_bib7","first-page":"1","article-title":"MSTrans: Multi-Scale Transformer for Building Extraction from High-Resolution Remote Sensing Images","volume":"62","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.procs.2025.09.324_bib8","unstructured":"Khomiakov, M., Andersen, M. R., & Frellsen, J. (2024). GeoFormer: A Multi-Polygon Segmentation Transformer. arXiv preprint arXiv:2411.16616."},{"key":"10.1016\/j.procs.2025.09.324_bib9","unstructured":"Kaur, N., et al. (2022). Large-Scale Building Damage Assessment Using a Novel Hierarchical Transformer Architecture on Satellite Images. arXiv preprint arXiv:2208.02205."},{"key":"10.1016\/j.procs.2025.09.324_bib10","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.3390\/s24041268","article-title":"Siamese Transformer-Based Building Change Detection in Remote Sensing Images","volume":"24","author":"Xiong","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.procs.2025.09.324_bib11","first-page":"70019","article-title":"Method for Extracting Buildings from Remote Sensing Images Based on UNet3+ with a 3D Joint Attention Module","volume":"14","author":"3DJA-UNet3+:","year":"2024","journal-title":"Scientific Reports"},{"key":"10.1016\/j.procs.2025.09.324_bib12","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al. (2021). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. IEEE\/CVF International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.procs.2025.09.324_bib13","doi-asserted-by":"crossref","unstructured":"Mohammadian, A., & Ghaderi, F. (2022). SiamixFormer: A Fully-Transformer Siamese Network with Temporal Fusion for Accurate Building Detection and Change Detection in Bi-Temporal Remote Sensing Images. arXiv preprint arXiv:2208.00657.","DOI":"10.1080\/01431161.2023.2225228"},{"issue":"11","key":"10.1016\/j.procs.2025.09.324_bib14","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.3390\/rs11111382","article-title":"End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++","volume":"11","author":"Peng","year":"2019","journal-title":"Remote Sensing"},{"key":"10.1016\/j.procs.2025.09.324_bib15","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.isprsjprs.2020.06.003","article-title":"A Deeply Supervised Image Fusion Network for Change Detection in High Resolution Bi-Temporal Remote Sensing Images","volume":"166","author":"Zhang","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.procs.2025.09.324_bib16","first-page":"1","article-title":"SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images","volume":"19","author":"Fang","year":"2022","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.procs.2025.09.324_bib17","doi-asserted-by":"crossref","unstructured":"Bandara, W. G. C., & Patel, V. M. (2022). A Transformer-Based Siamese Network for Change Detection. arXiv preprint arXiv:2201.01293.","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"10.1016\/j.procs.2025.09.324_bib18","unstructured":"Wang, L., et al. (2021). Building Extraction with Vision Transformer. arXiv preprint arXiv:2111.15637."},{"key":"10.1016\/j.procs.2025.09.324_bib19","doi-asserted-by":"crossref","unstructured":"E. S. Leni A., Revathi T., V. Dharmapuri, V. Punugott, and B. R. Gunta. (2025). Leveraging Transformer Architectures for Automated Building Detection in High-Resolution Satellite Images. 2025 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), Bangalore, India pp. 1 Doi: 10.1109\/IITCEE64140.2025.10915405","DOI":"10.1109\/IITCEE64140.2025.10915405"},{"key":"10.1016\/j.procs.2025.09.324_bib20","doi-asserted-by":"crossref","unstructured":"R. Wang, H. Jiang and Y. Li, \"UPerNet with ConvNeXt for Semantic Segmentation,\" 2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China, 2023 pp. 764 Doi: 10.1109\/ICETCI57876.2023.10177013","DOI":"10.1109\/ICETCI57876.2023.10177013"},{"key":"10.1016\/j.procs.2025.09.324_bib21","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., & Wang, M. (2022, October). Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision (pp. 205-218).","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"10.1016\/j.procs.2025.09.324_bib22","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems, 34, 12077-12090."}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925029977?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925029977?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:38:32Z","timestamp":1766306312000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050925029977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":22,"alternative-id":["S1877050925029977"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.324","relation":{},"ISSN":["1877-0509"],"issn-type":[{"type":"print","value":"1877-0509"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hybrid Transformer-Based Framework for Building Detection in High-Resolution Satellite Imagery: Integrating SAM, PVT, and Mask2Former","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.324","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}