{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:38:51Z","timestamp":1777336731634,"version":"3.51.4"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100016377","name":"North Rhine-Westphalia State Ministry of Economic Affairs Industry Climate Action and Energy","doi-asserted-by":"publisher","award":["005-2211-0002"],"award-info":[{"award-number":["005-2211-0002"]}],"id":[{"id":"10.13039\/501100016377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["520459685"],"award-info":[{"award-number":["520459685"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","award":["101073307"],"award-info":[{"award-number":["101073307"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133587","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T16:48:53Z","timestamp":1775494133000},"page":"133587","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Evaluating automatic label noise detection in 3D segmentation with realistic label noise"],"prefix":"10.1016","volume":"684","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9620-1292","authenticated-orcid":false,"given":"Andreas","family":"Mazur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3875-729X","authenticated-orcid":false,"given":"Isaac","family":"Roberts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3386-2577","authenticated-orcid":false,"given":"David P.","family":"Leins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0739-612X","authenticated-orcid":false,"given":"Alexander","family":"Schulz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-5591","authenticated-orcid":false,"given":"Barbara","family":"Hammer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133587_bib0005","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","article-title":"Geometric deep learning on molecular representations","volume":"3","author":"Atz","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133587_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2024.104062","article-title":"Human-in-the-loop: using classifier decision boundary maps to improve pseudo labels","volume":"124","author":"Benato","year":"2024","journal-title":"Comput. Graph."},{"key":"10.1016\/j.neucom.2026.133587_bib0015","series-title":"International Workshop on Text, Speech and Dialogue","first-page":"27","article-title":"Ensemble of classifiers for noise detection in PoS tagged corpora","author":"Berthelsen","year":"2000"},{"key":"10.1016\/j.neucom.2026.133587_bib0020","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3794","article-title":"Faust: dataset and evaluation for 3d mesh registration","author":"Bogo","year":"2014"},{"key":"10.1016\/j.neucom.2026.133587_bib0025","series-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NeurIPS)","first-page":"3197","article-title":"Learning shape correspondence with anisotropic convolutional neural networks","author":"Boscaini","year":"2016"},{"key":"10.1016\/j.neucom.2026.133587_bib0030","series-title":"European Conference on Computer Vision (ECCV)","first-page":"446","article-title":"Food-101 \u2013 mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.neucom.2026.133587_bib0035","author":"Bronstein"},{"key":"10.1016\/j.neucom.2026.133587_bib0040","author":"Chang"},{"key":"10.1016\/j.neucom.2026.133587_bib0045","series-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","author":"Chen","year":"2019"},{"key":"10.1016\/j.neucom.2026.133587_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7020","article-title":"Clip2scene: towards label-efficient 3D scene understanding by CLIP","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.133587_bib0055","series-title":"Equivariant Convolutional Networks","author":"Cohen","year":"2021"},{"key":"10.1016\/j.neucom.2026.133587_bib0060","series-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","first-page":"1321","article-title":"Gauge equivariant convolutional networks and the icosahedral CNN","author":"Cohen","year":"2019"},{"key":"10.1016\/j.neucom.2026.133587_bib0065","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1145\/3131280","article-title":"The heat method for distance computation","volume":"60","author":"Crane","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.neucom.2026.133587_bib0070","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","article-title":"Classification in the presence of label noise: a survey","volume":"25","author":"Fr\u00e9nay","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133587_bib0075","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Training deep neural-networks using a noise adaptation layer","author":"Goldberger","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0080","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1007\/s10994-022-06207-7","article-title":"An instance-dependent simulation framework for learning with label noise","volume":"112","author":"Gu","year":"2023","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133587_bib0085","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Gauge equivariant mesh CNNs: anisotropic convolutions on geometric graphs","author":"De Haan","year":"2021"},{"key":"10.1016\/j.neucom.2026.133587_bib0090","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Co-Teaching: robust training of deep neural networks with extremely noisy labels","author":"Han","year":"2018"},{"key":"10.1016\/j.neucom.2026.133587_bib0095","series-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","first-page":"2304","article-title":"MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels","author":"Jiang","year":"2018"},{"key":"10.1016\/j.neucom.2026.133587_bib0100","author":"Kim"},{"key":"10.1016\/j.neucom.2026.133587_bib0105","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.neucom.2026.133587_bib0110","series-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"Koh","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0115","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5447","article-title":"CleanNet: transfer learning for scalable image classifier training with label noise","author":"Lee","year":"2018"},{"key":"10.1016\/j.neucom.2026.133587_bib0120","author":"Li"},{"key":"10.1016\/j.neucom.2026.133587_bib0125","author":"Li"},{"key":"10.1016\/j.neucom.2026.133587_bib0130","series-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","first-page":"3355","article-title":"Dimensionality-Driven learning with noisy labels","author":"Ma","year":"2018"},{"key":"10.1016\/j.neucom.2026.133587_bib0135","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Decoupling \u201cwhen to update\u201d from \u201chow to update\u201d","author":"Malach","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0140","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops","first-page":"37","article-title":"Geodesic convolutional neural networks on riemannian manifolds","author":"Masci","year":"2015"},{"key":"10.1016\/j.neucom.2026.133587_bib0145","doi-asserted-by":"crossref","first-page":"649","DOI":"10.14428\/esann\/2024.ES2024-135","article-title":"Visualizing and improving 3D mesh segmentation with DeepView","author":"Mazur","year":"2024","journal-title":"ESANN 2024 Proc."},{"key":"10.1016\/j.neucom.2026.133587_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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.neucom.2026.133587_bib0155","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5115","article-title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","author":"Monti","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0160","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1613\/jair.1.12125","article-title":"Confident learning: estimating uncertainty in dataset labels","volume":"70","author":"Northcutt","year":"2021","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.133587_bib0165","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1944","article-title":"Making deep neural networks robust to label noise: a loss correction approach","author":"Patrini","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"815","article-title":"OpenScene: 3D scene understanding with open vocabularies","author":"Peng","year":"2023"},{"key":"10.1016\/j.neucom.2026.133587_bib0175","series-title":"World Conference on Explainable Artificial Intelligence","first-page":"193","article-title":"Influenci\u00e6: a library for tracing the influence back to the data-points","author":"Picard","year":"2024"},{"key":"10.1016\/j.neucom.2026.133587_bib0180","doi-asserted-by":"crossref","DOI":"10.1145\/3272127.3275102","article-title":"Multi-Directional geodesic neural networks via equivariant convolution","volume":"37","author":"Poulenard","year":"2018","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.133587_bib0185","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"652","article-title":"PointNet: deep learning on point sets for 3D classification and segmentation","author":"Qi","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0190","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"5105","article-title":"PointNet++: deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"key":"10.1016\/j.neucom.2026.133587_bib0195","series-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.133587_bib0200","author":"Ravi"},{"key":"10.1016\/j.neucom.2026.133587_bib0205","author":"Reed"},{"key":"10.1016\/j.neucom.2026.133587_bib0210","first-page":"251","article-title":"SHOT: unique signatures of histograms for surface and texture description","volume":"125","author":"Salti","year":"2014"},{"key":"10.1016\/j.neucom.2026.133587_bib0215","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Generalized learning vector quantization","author":"Sato","year":"1995"},{"key":"10.1016\/j.neucom.2026.133587_bib0220","series-title":"Proceedings of IJCAI-20, International Joint Conferences on Artificial Intelligence Organization","first-page":"2305","article-title":"DeepView: visualizing classification boundaries of deep neural networks as scatter plots using discriminative dimensionality reduction","author":"Schulz","year":"2020"},{"key":"10.1016\/j.neucom.2026.133587_bib0225","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1016\/j.icte.2024.09.007","article-title":"A review on label cleaning techniques for learning with noisy labels","volume":"10","author":"Shin","year":"2024","journal-title":"ICT Express"},{"key":"10.1016\/j.neucom.2026.133587_bib0230","doi-asserted-by":"crossref","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","article-title":"Learning from noisy labels with deep neural networks: a survey","volume":"34","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133587_bib0235","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Symmetric cross entropy for robust learning with noisy labels","author":"Wang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133587_bib0240","series-title":"Equivariant and Coordinate Independent Convolutional Networks \u2013 a Gauge Field Theory of Neural Networks","author":"Weiler","year":"2021"},{"key":"10.1016\/j.neucom.2026.133587_bib0245","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1023\/A:1007626913721","article-title":"Reduction techniques for Instance-Based learning algorithms","volume":"38","author":"Wilson","year":"2000","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133587_bib0250","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"21382","article-title":"A topological filter for learning with label noise","author":"Wu","year":"2020"},{"key":"10.1016\/j.neucom.2026.133587_bib0255","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"Xiao","year":"2015"},{"key":"10.1016\/j.neucom.2026.133587_bib0260","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Learning object bounding boxes for 3D instance segmentation on point clouds","author":"Yang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133587_bib0265","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6443","article-title":"Learning with noisy labels for robust point cloud segmentation","author":"Ye","year":"2021"},{"key":"10.1016\/j.neucom.2026.133587_bib0270","series-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","author":"Yu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133587_bib0275","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.133587_bib0280","doi-asserted-by":"crossref","first-page":"4398","DOI":"10.1109\/TPAMI.2024.3355425","article-title":"BadLabel: a robust perspective on evaluating and enhancing Label-Noise learning","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133587_bib0285","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11086","article-title":"AdaCo: overcoming visual foundation model noise in 3D semantic segmentation via adaptive label correction","author":"Zou","year":"2025"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009847?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009847?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T23:44:25Z","timestamp":1777333465000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226009847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":57,"alternative-id":["S0925231226009847"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133587","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating automatic label noise detection in 3D segmentation with realistic label noise","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133587","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133587"}}