{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T18:00:38Z","timestamp":1780768838724,"version":"3.54.1"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006683","name":"Xi'an Jiaotong-Liverpool University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.eswa.2026.132949","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T06:44:16Z","timestamp":1779259456000},"page":"132949","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards accurate urban scene understanding using point clouds: The SemanticUrban dataset"],"prefix":"10.1016","volume":"328","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-6066","authenticated-orcid":false,"given":"Yuan","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4847-3555","authenticated-orcid":false,"given":"Qinfeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7005-5870","authenticated-orcid":false,"given":"Yuanzhi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5538-4684","authenticated-orcid":false,"given":"Lei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132949_bib0001","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"1534","article-title":"3D semantic parsing of large-scale indoor spaces","author":"Armeni","year":"2016"},{"key":"10.1016\/j.eswa.2026.132949_bib0002","unstructured":"Beck, M., P\u00f6ppel, K., Spanring, M., Auer, A., Prudnikova, O., Kopp, M., Klambauer, G., Brandstetter, J., & Hochreiter, S. (2024). xLSTM: Extended long short-term memory. arXiv: 2405.04517."},{"key":"10.1016\/j.eswa.2026.132949_bib0003","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"9297","article-title":"SemanticKITTI: A dataset for semantic scene understanding of lidar sequences","author":"Behley","year":"2019"},{"key":"10.1016\/j.eswa.2026.132949_bib0004","doi-asserted-by":"crossref","first-page":"105","DOI":"10.5194\/isprs-annals-VIII-4-W2-2021-105-2021","article-title":"Integration of 3D point clouds with semantic 3d city models\u2013providing semantic information beyond classification","volume":"8","author":"Beil","year":"2021","journal-title":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences"},{"issue":"11","key":"10.1016\/j.eswa.2026.132949_bib0005","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.3390\/rs12111729","article-title":"Deep learning on 3d point clouds","volume":"12","author":"Bello","year":"2020","journal-title":"Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0006","first-page":"1","article-title":"Semantic segmentation of terrestrial laser scanning point clouds using locally enhanced image-based geometric representations","volume":"60","author":"Cai","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0007","unstructured":"Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H. et al. (2015). ShapeNet: An information-rich 3d model repository. arXiv: 1512.03012."},{"key":"10.1016\/j.eswa.2026.132949_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","article-title":"4D spatio-temporal convnets: Minkowski convolutional neural networks","author":"Choy","year":"2019"},{"key":"10.1016\/j.eswa.2026.132949_bib0009","series-title":"Medical image computing and computer-assisted intervention\u2013MICCAI 2016: 19th international conference, athens, greece, october 17\u201321, 2016, proceedings, part II 19","first-page":"424","article-title":"3D U-net: Learning dense volumetric segmentation from sparse annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"10.1016\/j.eswa.2026.132949_bib0010","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"5828","article-title":"ScanNet: Richly-annotated 3D reconstructions of indoor scenes","author":"Dai","year":"2017"},{"key":"10.1016\/j.eswa.2026.132949_bib0011","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s12518-017-0186-y","article-title":"Automation of point cloud processing to increase the deformation monitoring accuracy","volume":"9","author":"Erd\u00e9lyi","year":"2017","journal-title":"Applied Geomatics"},{"key":"10.1016\/j.eswa.2026.132949_bib0012","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.inffus.2020.11.002","article-title":"Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy","volume":"68","author":"Fernandes","year":"2021","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132949_bib0013","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.isprsjprs.2021.07.008","article-title":"Sum: A benchmark dataset of semantic urban meshes","volume":"179","author":"Gao","year":"2021","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0014","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv: 2312.00752."},{"key":"10.1016\/j.eswa.2026.132949_bib0015","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"PCT: Point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Computational Visual Media"},{"issue":"12","key":"10.1016\/j.eswa.2026.132949_bib0016","doi-asserted-by":"crossref","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep learning for 3D point clouds: A survey","volume":"43","author":"Guo","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132949_bib0017","doi-asserted-by":"crossref","unstructured":"Hackel, T., Savinov, N., Ladicky, L., Wegner, J. D., Schindler, K., & Pollefeys, M. (2017). Semantic3d. net: A new large-scale point cloud classification benchmark. arXiv: 1704.03847.","DOI":"10.5194\/isprs-annals-IV-1-W1-91-2017"},{"key":"10.1016\/j.eswa.2026.132949_bib0018","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.isprsjprs.2024.02.007","article-title":"WHU-Urban3D: An urban scene lidar point cloud dataset for semantic instance segmentation","volume":"209","author":"Han","year":"2024","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0019","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.isprsjprs.2024.02.007","article-title":"WHU-Urban3D: An urban scene lidar point cloud dataset for semantic instance segmentation","volume":"209","author":"Han","year":"2024","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"4977","article-title":"Towards semantic segmentation of urban-scale 3D point clouds: A dataset, benchmarks and challenges","author":"Hu","year":"2021"},{"key":"10.1016\/j.eswa.2026.132949_bib0021","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.autcon.2018.01.009","article-title":"Slam-driven robotic mapping and registration of 3d point clouds","volume":"89","author":"Kim","year":"2018","journal-title":"Automation in Construction"},{"key":"10.1016\/j.eswa.2026.132949_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.ophoto.2021.100001","article-title":"The hessigheim 3d (h3d) benchmark on semantic segmentation of high-resolution 3D point clouds and textured meshes from UAV liDAR and multi-view-stereo","volume":"1","author":"K\u00f6lle","year":"2021","journal-title":"ISPRS Open Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0023","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s11263-012-0517-8","article-title":"Creating large-scale city models from 3D-point clouds: A robust approach with hybrid representation","volume":"99","author":"Lafarge","year":"2012","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132949_bib0024","series-title":"2011\u202fIEEE International conference on robotics and automation","first-page":"1817","article-title":"A large-scale hierarchical multi-view rgb-d object dataset","author":"Lai","year":"2011"},{"key":"10.1016\/j.eswa.2026.132949_bib0025","series-title":"Computer analysis of images and patterns: 17th International conference, CAIP 2017, ystad, Sweden, August 22\u201324, 2017, proceedings, part I 17","first-page":"95","article-title":"Deep projective 3D semantic segmentation","author":"Lawin","year":"2017"},{"key":"10.1016\/j.eswa.2026.132949_bib0026","series-title":"Proceedings of the 28th ACM International conference on multimedia","first-page":"238","article-title":"Campus3D: A photogrammetry point cloud benchmark for hierarchical understanding of outdoor scene","author":"Li","year":"2020"},{"key":"10.1016\/j.eswa.2026.132949_bib0027","unstructured":"Liang, D., Zhou, X., Xu, W., Zhu, X., Zou, Z., Ye, X., Tan, X., & Bai, X. (2024). PointMamba: A simple state space model for point cloud analysis. arXiv: 2402.10739."},{"key":"10.1016\/j.eswa.2026.132949_bib0028","unstructured":"Lieber, O., Lenz, B., Bata, H., Cohen, G., Osin, J., Dalmedigos, I., Safahi, E., Meirom, S., Belinkov, Y., Shalev-Shwartz, S. et al. (2024). Jamba: A hybrid transformer-mamba language model. arXiv: 2403.19887."},{"key":"10.1016\/j.eswa.2026.132949_bib0029","first-page":"1","article-title":"Rs 3 Mamba: Visual state space model for remote sensing image semantic segmentation","volume":"21","author":"Ma","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"16","key":"10.1016\/j.eswa.2026.132949_bib0030","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.3390\/rs11161940","article-title":"Structure from motion point clouds for structural monitoring","volume":"11","author":"Mistretta","year":"2019","journal-title":"Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132949_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"909","article-title":"PartNet: A large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding","author":"Mo","year":"2019"},{"key":"10.1016\/j.eswa.2026.132949_bib0032","series-title":"2013 6th IEEE Conference on robotics, automation and mechatronics (RAM)","first-page":"225","article-title":"3D point cloud segmentation: A survey","author":"Nguyen","year":"2013"},{"key":"10.1016\/j.eswa.2026.132949_bib0033","series-title":"Open source geospatial science for urban studies: The value of open geospatial data","first-page":"97","article-title":"Generating 3D city models from open LiDAR point clouds: Advancing towards smart city applications","author":"Ortega","year":"2021"},{"key":"10.1016\/j.eswa.2026.132949_bib0034","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"Qi","year":"2017"},{"key":"10.1016\/j.eswa.2026.132949_bib0035","series-title":"Advances in neural information processing systems","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"vol. 30","author":"Qi","year":"2017"},{"issue":"6","key":"10.1016\/j.eswa.2026.132949_bib0036","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1177\/0278364918767506","article-title":"Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification","volume":"37","author":"Roynard","year":"2018","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.eswa.2026.132949_bib0037","series-title":"European conference on computer vision","first-page":"125","article-title":"Language-grounded indoor 3D semantic segmentation in the wild","author":"Rozenberszki","year":"2022"},{"key":"10.1016\/j.eswa.2026.132949_bib0038","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"18433","article-title":"Point-slam: Dense neural point cloud-based slam","author":"Sandstr\u00f6m","year":"2023"},{"key":"10.1016\/j.eswa.2026.132949_bib0039","series-title":"European conference on computer vision","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"Silberman","year":"2012"},{"key":"10.1016\/j.eswa.2026.132949_bib0040","series-title":"Proceedings of the IEEE International conference on computer vision","first-page":"945","article-title":"Multi-view convolutional neural networks for 3D shape recognition","author":"Su","year":"2015"},{"key":"10.1016\/j.eswa.2026.132949_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition workshops","first-page":"202","article-title":"Toronto-3D: A large-scale mobile liDAR dataset for semantic segmentation of urban roadways","author":"Tan","year":"2020"},{"key":"10.1016\/j.eswa.2026.132949_bib0042","series-title":"2017 International conference on 3D vision (3DV)","first-page":"537","article-title":"SegCloud: Semantic segmentation of 3d point clouds","author":"Tchapmi","year":"2017"},{"key":"10.1016\/j.eswa.2026.132949_bib0043","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"6411","article-title":"KPConv: Flexible and deformable convolution for point clouds","author":"Thomas","year":"2019"},{"key":"10.1016\/j.eswa.2026.132949_bib0044","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition workshops","first-page":"186","article-title":"Dales: A large-scale aerial lidar data set for semantic segmentation","author":"Varney","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.132949_bib0045","first-page":"1","article-title":"Octformer: Octree-based transformers for 3d point clouds","volume":"42","author":"Wang","year":"2023","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10.1016\/j.eswa.2026.132949_bib0046","series-title":"European conference on computer vision","first-page":"403","article-title":"SFPNet: Sparse focal point network for semantic segmentation on general lidar point clouds","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132949_bib0047","series-title":"Advances in neural information processing systems","first-page":"33330","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","volume":"vol. 35","author":"Wu","year":"2022"},{"issue":"4","key":"10.1016\/j.eswa.2026.132949_bib0048","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MGRS.2019.2937630","article-title":"Linking points with labels in 3D: A review of point cloud semantic segmentation","volume":"8","author":"Xie","year":"2020","journal-title":"IEEE Geoscience and Remote Sensing Magazine"},{"issue":"7","key":"10.1016\/j.eswa.2026.132949_bib0049","doi-asserted-by":"crossref","first-page":"450","DOI":"10.3390\/ijgi9070450","article-title":"Lasdu: A large-scale aerial lidar dataset for semantic labeling in dense urban areas","volume":"9","author":"Ye","year":"2020","journal-title":"ISPRS International Journal of Geo-Information"},{"key":"10.1016\/j.eswa.2026.132949_bib0050","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"12","article-title":"ScanNet++: A high-fidelity dataset of 3D indoor scenes","author":"Yeshwanth","year":"2023"},{"key":"10.1016\/j.eswa.2026.132949_bib0051","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"19313","article-title":"Point-BERT: Pre-training 3D point cloud transformers with masked point modeling","author":"Yu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132949_bib0052","doi-asserted-by":"crossref","first-page":"179118","DOI":"10.1109\/ACCESS.2019.2958671","article-title":"A review of deep learning-based semantic segmentation for point cloud","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132949_bib0053","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"16259","article-title":"Point transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.eswa.2026.132949_bib0054","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision (ICCV)","first-page":"16259","article-title":"Point transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.eswa.2026.132949_bib0055","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"562","article-title":"Divide and conquer: 3D point cloud instance segmentation with point-wise binarization","author":"Zhao","year":"2023"},{"key":"10.1016\/j.eswa.2026.132949_bib0056","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"29395","article-title":"BFANet: Revisiting 3D semantic segmentation with boundary feature analysis","author":"Zhao","year":"2025"},{"issue":"19","key":"10.1016\/j.eswa.2026.132949_bib0057","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e38495","article-title":"Samba: Semantic segmentation of remotely sensed images with state space model","volume":"10","author":"Zhu","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.eswa.2026.132949_bib0058","article-title":"Advancements in point cloud data augmentation for deep learning: A survey","author":"Zhu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132949_bib0059","unstructured":"Zolanvari, S. M., Ruano, S., Rana, A., Cummins, A., Da Silva, R. E., Rahbar, M., & Smolic, A. (2019). Dublincity: Annotated LiDAR point cloud and its applications. arXiv: 1909.03613."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018610?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018610?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:40:12Z","timestamp":1780767612000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426018610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":59,"alternative-id":["S0957417426018610"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132949","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards accurate urban scene understanding using point clouds: The SemanticUrban dataset","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132949","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132949"}}