{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:31:18Z","timestamp":1780054278479,"version":"3.54.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198236","type":"print"},{"value":"9783031198243","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19824-3_32","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T21:14:32Z","timestamp":1668114872000},"page":"543-560","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["4DContrast: Contrastive Learning with\u00a0Dynamic Correspondences for\u00a03D Scene Understanding"],"prefix":"10.1007","author":[{"given":"Yujin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: International Conference on 3D Vision, pp. 667\u2013676 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"32_CR2","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 (2020)"},{"key":"32_CR3","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Shape self-correction for unsupervised point cloud understanding. In: International Conference on Computer Vision, pp. 8382\u20138391 (2021)","DOI":"10.1109\/ICCV48922.2021.00827"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"32_CR7","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: Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"32_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1007\/978-3-030-01249-6_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Dai","year":"2018","unstructured":"Dai, A., Nie\u00dfner, M.: 3DMV: joint 3D-multi-view prediction for 3D semantic scene segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 458\u2013474. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_28"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Bokeloh, M., Fathi, A., Leibe, B., Nie\u00dfner, M.: 3D-MPA: multi-proposal aggregation for 3D semantic instance segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 9031\u20139040 (2020)","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"32_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, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"32_CR12","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Han, L., Zheng, T., Xu, L., Fang, L.: OccuSeg: occupancy-aware 3D instance segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 2940\u20132949 (2020)","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: International Conference on Computer Vision, pp. 8160\u20138171 (2019)","DOI":"10.1109\/ICCV.2019.00825"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Nie\u00dfner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans. In: Conference on Computer Vision and Pattern Recognition, pp. 4421\u20134430 (2019)","DOI":"10.1109\/CVPR.2019.00455"},{"key":"32_CR17","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: Conference on Computer Vision and Pattern Recognition, pp. 15587\u201315597 (2021)","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Hu, W., Zhao, H., Jiang, L., Jia, J., Wong, T.T.: Bidirectional projection network for cross dimension scene understanding. In: Conference on Computer Vision and Pattern Recognition, pp. 14373\u201314382 (2021)","DOI":"10.1109\/CVPR46437.2021.01414"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhang, H., Yi, L., Funkhouser, T., Nie\u00dfner, M., Guibas, L.J.: TextureNet: consistent local parametrizations for learning from high-resolution signals on meshes. In: Conference on Computer Vision and Pattern Recognition, pp. 4440\u20134449 (2019)","DOI":"10.1109\/CVPR.2019.00457"},{"key":"32_CR20","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, pp. 6535\u20136545 (2021)","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.W., Jia, J.: PointGroup: dual-set point grouping for 3D instance segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 4867\u20134876 (2020)","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Kundu, A., et al.: Virtual multi-view fusion for 3D semantic segmentation. In: European Conference on Computer Vision, pp. 518\u2013535 (2020)","DOI":"10.1007\/978-3-030-58586-0_31"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Liang, H., et al.: Exploring geometry-aware contrast and clustering harmonization for self-supervised 3D object detection. In: International Conference on Computer Vision, pp. 3293\u20133302 (2021)","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Nekrasov, A., Schult, J., Litany, O., Leibe, B., Engelmann, F.: Mix3D: out-of-context data augmentation for 3D scenes. In: 2021 International Conference on 3D Vision (3DV), pp. 116\u2013125. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Nie, Y., Hou, J., Han, X., Nie\u00dfner, M.: RFD-net: point scene understanding by semantic instance reconstruction. In: Conference on Computer Vision and Pattern Recognition, pp. 4608\u20134618 (2021)","DOI":"10.1109\/CVPR46437.2021.00458"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Chen, X., Litany, O., Guibas, L.J.: ImvoteNet: boosting 3D object detection in point clouds with image votes. In: Conference on Computer Vision and Pattern Recognition, pp. 4404\u20134413 (2020)","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"32_CR29","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"32_CR30","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Neural Information Processing Systems (2017)"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Rao, Y., Liu, B., Wei, Y., Lu, J., Hsieh, C.J., Zhou, J.: RandomRooms: unsupervised pre-training from synthetic shapes and randomized layouts for 3D object detection. In: International Conference on Computer Vision, pp. 3283\u20133292 (2021)","DOI":"10.1109\/ICCV48922.2021.00327"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. arXiv preprint arXiv:2204.07761 (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"32_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-030-58526-6_37","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Sanghi","year":"2020","unstructured":"Sanghi, A.: Info3D: representation learning on 3D objects using mutual information maximization and contrastive learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 626\u2013642. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_37"},{"key":"32_CR34","unstructured":"Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. In: Neural Information Processing Systems (2019)"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Kontogianni, T., Leibe, B.: DualconvMesh-net: joint geodesic and Euclidean convolutions on 3D meshes. In: Conference on Computer Vision and Pattern Recognition, pp. 8612\u20138622 (2020)","DOI":"10.1109\/CVPR42600.2020.00864"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: Conference on Computer Vision and Pattern Recognition, pp. 808\u2013816 (2016)","DOI":"10.1109\/CVPR.2016.94"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: International Conference on Computer Vision, pp. 945\u2013953 (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"32_CR39","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, pp. 9782\u20139792 (2021)","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Wang, P.S., Yang, Y.Q., Zou, Q.F., Wu, Z., Liu, Y., Tong, X.: Unsupervised 3D learning for shape analysis via multiresolution instance discrimination, vol. 35, pp. 2773\u20132781 (2021)","DOI":"10.1609\/aaai.v35i4.16382"},{"key":"32_CR41","unstructured":"Wu, Z., et al.: 3D shapenets: a deep representation for volumetric shapes. In: Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)"},{"key":"32_CR42","doi-asserted-by":"crossref","unstructured":"Xie, Q., et al.: MlcvNet: multi-level context votenet for 3D object detection. In: Conference on Computer Vision and Pattern Recognition, pp. 10447\u201310456 (2020)","DOI":"10.1109\/CVPR42600.2020.01046"},{"key":"32_CR43","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. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Yi, L., Zhao, W., Wang, H., Sung, M., Guibas, L.J.: GSPN: generative shape proposal network for 3D instance segmentation in point cloud. In: Conference on Computer Vision and Pattern Recognition, pp. 3947\u20133956 (2019)","DOI":"10.1109\/CVPR.2019.00407"},{"key":"32_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wonka, P.: Point cloud instance segmentation using probabilistic embeddings. In: Conference on Computer Vision and Pattern Recognition, pp. 8883\u20138892 (2021)","DOI":"10.1109\/CVPR46437.2021.00877"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: International Conference on Computer Vision, pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"32_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58610-2_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3DNet: 3D object detection using hybrid geometric primitives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 311\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_19"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19824-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T00:15:50Z","timestamp":1668212150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19824-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198236","9783031198243"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19824-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}