{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:18:03Z","timestamp":1743009483550,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031733468"},{"type":"electronic","value":"9783031733475"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73347-5_27","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"475-491","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Equivariant Spatio-temporal Self-supervision for\u00a0LiDAR Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7046-7891","authenticated-orcid":false,"given":"Deepti","family":"Hegde","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-3818","authenticated-orcid":false,"given":"Suhas","family":"Lohit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2682-9912","authenticated-orcid":false,"given":"Kuan-Chuan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5215-2346","authenticated-orcid":false,"given":"Michael J.","family":"Jones","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5239-692X","authenticated-orcid":false,"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"27_CR1","unstructured":"Bhardwaj, S., et al.: Steerable equivariant representation learning. arXiv preprint arXiv:2302.11349 (2023)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Boulch, A., Sautier, C., Michele, B., Puy, G., Marlet, R.: ALSO: automotive lidar self-supervision by occupancy estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13455\u201313465 (2023)","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"27_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"27_CR5","unstructured":"Dangovski, R., et al.: Equivariant self-supervised learning: encouraging equivariance in representations. In: International Conference on Learning Representations (2022)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"27_CR7","unstructured":"Devillers, A., Lefort, M.: EquiMod: an equivariance module to improve self-supervised learning. arXiv preprint arXiv:2211.01244 (2022)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Embracing single stride 3D object detector with sparse transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8458\u20138468 (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"27_CR9","unstructured":"Garrido, Q., Najman, L., Lecun, Y.: Self-supervised learning of split invariant equivariant representations. In: The Fortieth International Conference on Machine Learning (2023)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"27_CR11","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"27_CR12","unstructured":"Gupta, S., Robinson, J., Lim, D., Villar, S., Jegelka, S.: Learning structured representations with equivariant contrastive learning. In: ICML Workshop on Topology, Algebra, and Geometry in Machine Learning (2023)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u2019ar, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. 2022 IEEE. In: CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15979\u201315988 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"27_CR15","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6535\u20136545 (2021)","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Jin, Z., Lei, Y., Akhtar, N., Li, H., Hayat, M.: Deformation and correspondence aware unsupervised synthetic-to-real scene flow estimation for point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7233\u20137243 (2022)","DOI":"10.1109\/CVPR52688.2022.00709"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Liao, Y., Xie, J., Geiger, A.: KITTI-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. Pattern Anal. Mach. Intell. (PAMI) (2022)","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"27_CR19","unstructured":"Mao, J., et\u00a0al.: One million scenes for autonomous driving: once dataset. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)"},{"issue":"2","key":"27_CR20","doi-asserted-by":"publisher","first-page":"2116","DOI":"10.1109\/LRA.2022.3142440","volume":"7","author":"L Nunes","year":"2022","unstructured":"Nunes, L., Marcuzzi, R., Chen, X., Behley, J., Stachniss, C.: SegContrast: 3D point cloud feature representation learning through self-supervised segment discrimination. IEEE Robot. Autom. Lett. 7(2), 2116\u20132123 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Nunes, L., Wiesmann, L., Marcuzzi, R., Chen, X., Behley, J., Stachniss, C.: Temporal consistent 3D LiDAR representation learning for semantic perception in autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5217\u20135228 (2023)","DOI":"10.1109\/CVPR52729.2023.00505"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"issue":"2","key":"27_CR23","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., et al.: PV-RCNN++: point-voxel feature set abstraction with local vector representation for 3D object detection. Int. J. Comput. Vision 131(2), 531\u2013551 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"08","key":"27_CR25","first-page":"2647","volume":"43","author":"S Shi","year":"2021","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. 43(08), 2647\u20132664 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"27_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/978-3-030-58604-1_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tang","year":"2020","unstructured":"Tang, H., et al.: Searching efficient 3D architectures with sparse point-voxel convolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 685\u2013702. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_41"},{"key":"27_CR28","unstructured":"Team, O.D.: OpenPCDet: an open-source toolbox for 3D object detection from point clouds (2020). https:\/\/github.com\/open-mmlab\/OpenPCDet"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, Z., Rao, Y., Lu, J., Zhou, J.: PV-RAFT: point-voxel correlation fields for scene flow estimation of point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6954\u20136963 (2021)","DOI":"10.1109\/CVPR46437.2021.00688"},{"key":"27_CR30","unstructured":"Xiao, T., Wang, X., Efros, A.A., Darrell, T.: What should not be contrastive in contrastive learning. In: International Conference on Learning Representations (2021)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"27_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58580-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xie","year":"2020","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part III. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Ren, M., Zeng, W., Urtasun, R.: Self-supervised representation learning from flow equivariance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10191\u201310200 (2021)","DOI":"10.1109\/ICCV48922.2021.01003"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Xu, R., et al.: MV-JAR: masked voxel jigsaw and reconstruction for LiDAR-based self-supervised pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13445\u201313454 (2023)","DOI":"10.1109\/CVPR52729.2023.01292"},{"key":"27_CR35","unstructured":"Yan, X., et al.: SPOT: scalable 3D pre-training via occupancy prediction for autonomous driving. arXiv preprint arXiv:2309.10527 (2023)"},{"key":"27_CR36","doi-asserted-by":"publisher","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10) (2018). https:\/\/doi.org\/10.3390\/s18103337, https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3337","DOI":"10.3390\/s18103337"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: GD-MAE: generative decoder for MAE pre-training on LiDAR point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9403\u20139414 (2023)","DOI":"10.1109\/CVPR52729.2023.00907"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"27_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-031-19842-7_2","volume-title":"Computer Vision - ECCV 2022","author":"J Yin","year":"2022","unstructured":"Yin, J., Zhou, D., Zhang, L., Fang, J., Xu, C.Z., Shen, J., Wang, W.: ProposalContrast: unsupervised pre-training for LiDAR-based 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13699, pp. 17\u201333. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_2"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Cylindrical and asymmetrical 3D convolution networks for LiDAR segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9939\u20139948 (2021)","DOI":"10.1109\/CVPR46437.2021.00981"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73347-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:54:44Z","timestamp":1730109284000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}