{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:17:02Z","timestamp":1777655822156,"version":"3.51.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031546044","type":"print"},{"value":"9783031546051","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-54605-1_9","type":"book-chapter","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:43:10Z","timestamp":1709811790000},"page":"131-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Point2Vec for\u00a0Self-supervised Representation Learning on\u00a0Point Clouds"],"prefix":"10.1007","author":[{"given":"Karim Abou","family":"Zeid","sequence":"first","affiliation":[]},{"given":"Jonas","family":"Schult","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Hermans","sequence":"additional","affiliation":[]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"9_CR2","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning (2022)"},{"key":"9_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Neural Information Processing Systems (2020)"},{"key":"9_CR4","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: International Conference on Learning Representations (2022)"},{"key":"9_CR5","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: Vicreg: variance-invariance-covariance regularization for self-supervised learning. In: International Conference on Learning Representations (2022)"},{"key":"9_CR6","unstructured":"Baruch, G., et al.: ARKitscenes - a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. In: Neural Information Processing Systems (2021)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: SemanticKITTI: a dataset for semantic scene understanding of LiDAR sequences. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"9_CR10","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"9_CR12","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning (2020)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: minkowski convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"9_CR16","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"9_CR17","unstructured":"Dong, R., et al.: Autoencoders as cross-modal teachers: can pretrained 2D image transformers help 3D representation learning? In: International Conference on Learning Representations (2023)"},{"key":"9_CR18","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Eckart, B., Yuan, W., Liu, C., Kautz, J.: Self-supervised learning on 3D point clouds by learning discrete generative models. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00815"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"9_CR21","unstructured":"Gao, M., et al.: ULIP: learning a unified representation of language, images, and point clouds for 3D understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (2023)"},{"key":"9_CR22","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Neural Information Processing Systems (2020)"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Hsu, W.N., Tsai, Y.H.H., Bolte, B., Salakhutdinov, R., Mohamed, A.: Hubert: how much can a bad teacher benefit ASR pre-training? In: IEEE Conference on Acoustics, Speech and Signal Processing (2021)","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Huang, S., Xie, Y., Zhu, S.C., Zhu, Y.: Spatio-temporal self-supervised representation learning for 3D point clouds. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Cai, M., Lee, Y.J.: Masked discrimination for self-supervised learning on point clouds. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"9_CR30","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017)"},{"key":"9_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"9_CR32","unstructured":"Ma, X., Qin, C., You, H., Ran, H., Fu, Y.: Rethinking network design and local geometry in point cloud: a simple residual MLP framework. In: International Conference on Learning Representations (2022)"},{"key":"9_CR33","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., Yuan, L.: Masked autoencoders for point cloud self-supervised learning. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"9_CR35","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)"},{"key":"9_CR36","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (2017)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lu, J., Zhou, J.: Global-local bidirectional reasoning for unsupervised representation learning of 3D point clouds. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00542"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D for 3D semantic instance segmentation. In: IEEE International Conference on Robotics and Automation (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"9_CR40","unstructured":"Sharma, C., Kaul, M.: Self-supervised few-shot learning on point clouds. In: Neural Information Processing Systems (2020)"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"9_CR42","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? In: Neural Information Processing Systems (2020)"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, D.T., Yeung, S.K.: Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00167"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, Q., Yue, X., Lasenby, J., Kusner, M.J.: Unsupervised point cloud pre-training via occlusion completion. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"9_CR45","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: International Conference on Computer Vision (2015)"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"9_CR47","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Neural Information Processing Systems (2019)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. In: SIGGRAPH Asia (2016)","DOI":"10.1145\/2980179.2980238"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., Lu, J.: Point-BERT: pre-training 3D point cloud transformers with masked point modeling. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"9_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Multi-scale vision longformer: a new vision transformer for high-resolution image encoding. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"9_CR51","unstructured":"Zhang, R., et al.: Point-M2AE: multi-scale masked autoencoders for hierarchical point cloud pre-training. In: Advances in Neural Information Processing Systems (2022)"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Pointclip: point cloud understanding by clip. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Qiao, Y., Gao, P., Li, H.: Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders. In: IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02085"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-54605-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:04:20Z","timestamp":1709813060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-54605-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031546044","9783031546051"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-54605-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heidelberg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"45","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/year\/2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"76","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"53% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}