{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T18:26:14Z","timestamp":1772043974617,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union\u2019s Horizon 2020 Research and Innovation Program","award":["101092875"],"award-info":[{"award-number":["101092875"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3388155","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:30:51Z","timestamp":1712943051000},"page":"53565-53578","source":"Crossref","is-referenced-by-count":3,"title":["ExpPoint-MAE: Better Interpretability and Performance for Self-Supervised Point Cloud Transformers"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2917-8705","authenticated-orcid":false,"given":"Ioannis","family":"Romanelis","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Patras, Patras, Greece"}]},{"given":"Vlassis","family":"Fotis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Patras, Patras, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7617-227X","authenticated-orcid":false,"given":"Konstantinos","family":"Moustakas","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Patras, Patras, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-0428","authenticated-orcid":false,"given":"Adrian","family":"Munteanu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref6","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref7","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Raghu"},{"key":"ref8","first-page":"1","article-title":"Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Nguyen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref10","first-page":"71","article-title":"Explaining the PointNet: What has been learned inside the PointNet?","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Zhang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_10"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref13","article-title":"When vision transformers outperform ResNets without pre-training or strong data augmentations","author":"Chen","year":"2021","journal-title":"arXiv:2106.01548"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240702"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref19","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref22","first-page":"1","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01547-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01752-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/int.23073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref35","article-title":"Handwritten digit recognition with a back-propagation network","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"LeCun"},{"key":"ref36","article-title":"On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Ng"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273592"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref40","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref41","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01555-8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref45","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00636"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00815"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475458"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01650-4"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"issue":"1","key":"ref56","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"Cortes","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref58","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191095"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref63","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","author":"Zhang","year":"2022","journal-title":"arXiv:2205.14401"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01813-x"},{"key":"ref65","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2021","journal-title":"arXiv:2106.10270"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10497601.pdf?arnumber=10497601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T17:33:08Z","timestamp":1713547988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10497601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3388155","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}