{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:58:28Z","timestamp":1775325508879,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73390-1_14","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"232-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Reliable Spatial-Temporal Voxels For Multi-modal Test-Time Adaptation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7703-3490","authenticated-orcid":false,"given":"Haozhi","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4292-7379","authenticated-orcid":false,"given":"Yuecong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8075-0439","authenticated-orcid":false,"given":"Jianfei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7470-0736","authenticated-orcid":false,"given":"Pengyu","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7694-6609","authenticated-orcid":false,"given":"Xingyu","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1887-6342","authenticated-orcid":false,"given":"Shenghai","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7137-4136","authenticated-orcid":false,"given":"Lihua","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9297\u20139307 (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cao, H., Xu, Y., Yang, J., Yin, P., Yuan, S., Xie, L.: Mopa: multi-modal prior aided domain adaptation for 3d semantic segmentation. arXiv preprint arXiv:2309.11839 (2023)","DOI":"10.1109\/ICCV51070.2023.01724"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cao, H., Xu, Y., Yang, J., Yin, P., Yuan, S., Xie, L.: Multi-modal continual test-time adaptation for 3d semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 18809\u201318819, October 2023","DOI":"10.1109\/ICCV51070.2023.01724"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Clip2scene: towards label-efficient 3d scene understanding by clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7020\u20137030 (2023)","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"14_CR6","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":"14_CR7","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point 4d transformer networks for spatio-temporal modeling in point cloud videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14204\u201314213 (2021)","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"14_CR8","unstructured":"Fan, H., Yu, X., Ding, Y., Yang, Y., Kankanhalli, M.: Pstnet: point spatio-temporal convolution on point cloud sequences. arXiv preprint arXiv:2205.13713 (2022)"},{"issue":"3","key":"14_CR9","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"14_CR10","unstructured":"Geyer, J., et\u00a0al.: A2d2: audi autonomous driving dataset. arXiv preprint arXiv:2004.06320 (2020)"},{"key":"14_CR11","unstructured":"Gong, T., Jeong, J., Kim, T., Kim, Y., Shin, J., Lee, S.J.: Robust continual test-time adaptation: Instance-aware bn and prediction-balanced memory. arXiv preprint arXiv:2208.05117 (2022)"},{"key":"14_CR12","unstructured":"Goyal, S., Sun, M., Raghunathan, A., Kolter, J.Z.: Test time adaptation via conjugate pseudo-labels. In: Advances in Neural Information Processing Systems (2022)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Graham, B.: Sparse 3d convolutional neural networks. arXiv preprint arXiv:1505.02890 (2015)","DOI":"10.5244\/C.29.150"},{"issue":"12","key":"14_CR14","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","volume":"43","author":"Y Guo","year":"2020","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3d point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4338\u20134364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Huang, S., Gojcic, Z., Huang, J., Wieser, A., Schindler, K.: Dynamic 3d scene analysis by point cloud accumulation. In: European Conference on Computer Vision, pp. 674\u2013690. Springer (2022)","DOI":"10.1007\/978-3-031-19839-7_39"},{"issue":"2","key":"14_CR16","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TPAMI.2022.3159589","volume":"45","author":"M Jaritz","year":"2022","unstructured":"Jaritz, M., Vu, T.H., De Charette, R., Wirbel, \u00c9., P\u00e9rez, P.: Cross-modal learning for domain adaptation in 3d semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1533\u20131544 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Ji, X., Yuan, S., Yin, P., Xie, L.: Lio-gvm: an accurate, tightly-coupled lidar-inertial odometry with gaussian voxel map. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3354616"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, Y., Xie, Y., Gao, Z., Li, C., Zhang, Z., Qu, Y.: Cross-domain and cross-modal knowledge distillation in domain adaptation for 3d semantic segmentation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3829\u20133837 (2022)","DOI":"10.1145\/3503161.3547990"},{"key":"14_CR19","unstructured":"Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 6028\u20136039. PMLR (2020)"},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.isprsjprs.2021.04.012","volume":"176","author":"W Liu","year":"2021","unstructured":"Liu, W., et al.: Adversarial unsupervised domain adaptation for 3d semantic segmentation with multi-modal learning. ISPRS J. Photogramm. Remote. Sens. 176, 211\u2013221 (2021)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"14_CR21","first-page":"21808","volume":"34","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Kothari, P., Van Delft, B., Bellot-Gurlet, B., Mordan, T., Alahi, A.: Ttt++: when does self-supervised test-time training fail or thrive? Adv. Neural. Inf. Process. Syst. 34, 21808\u201321820 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR22","unstructured":"Niu, S., et al.: Efficient test-time model adaptation without forgetting. In: International Conference on Machine Learning, pp. 16888\u201316905. PMLR (2022)"},{"key":"14_CR23","unstructured":"Niu, S., et al.: Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400 (2023)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Peng, D., Lei, Y., Li, W., Zhang, P., Guo, Y.: Sparse-to-dense feature matching: Intra and inter domain cross-modal learning in domain adaptation for 3d semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7108\u20137117 (2021)","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Casser, V., Ryoo, M.S., Angelova, A.: 4d-net for learned multi-modal alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15435\u201315445 (2021)","DOI":"10.1109\/ICCV48922.2021.01515"},{"key":"14_CR26","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"14_CR27","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Saltori, C., et al.: Gipso: geometrically informed propagation for online adaptation in 3d lidar segmentation. In: European Conference on Computer Vision, pp. 567\u2013585. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_33"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Shin, I., et al.: Mm-tta: multi-modal test-time adaptation for 3d semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16928\u201316937 (2022)","DOI":"10.1109\/CVPR52688.2022.01642"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Simons, C., Raychaudhuri, D.S., Ahmed, S.M., You, S., Karydis, K., Roy-Chowdhury, A.K.: Summit: Source-free adaptation of uni-modal models to multi-modal targets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1239\u20131249, October 2023","DOI":"10.1109\/ICCV51070.2023.00120"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Song, J., Lee, J., Kweon, I.S., Choi, S.: Ecotta: memory-efficient continual test-time adaptation via self-distilled regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11920\u201311929 (2023)","DOI":"10.1109\/CVPR52729.2023.01147"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Su, Y., Xu, X., Li, T., Jia, K.: Revisiting realistic test-time training: sequential inference and adaptation by anchored clustering regularized self-training. arXiv preprint arXiv:2303.10856 (2023)","DOI":"10.1109\/TPAMI.2024.3370963"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Tang, H., et al.: Searching efficient 3d architectures with sparse point-voxel convolution. In: European Conference on Computer Vision, pp. 685\u2013702. Springer (2020)","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"14_CR34","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems 30 (2017)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Vedula, S., Baker, S., Rander, P., Collins, R., Kanade, T.: Three-dimensional scene flow. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol.\u00a02, pp. 722\u2013729. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790293"},{"issue":"2","key":"14_CR36","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1109\/LRA.2023.3236571","volume":"8","author":"I Vizzo","year":"2023","unstructured":"Vizzo, I., Guadagnino, T., Mersch, B., Wiesmann, L., Behley, J., Stachniss, C.: Kiss-icp: in defense of point-to-point icp-simple, accurate, and robust registration if done the right way. IEEE Robot. Autom. Lett. 8(2), 1029\u20131036 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Vogel, C., Schindler, K., Roth, S.: 3d scene flow estimation with a rigid motion prior. In: 2011 International Conference on Computer Vision, pp. 1291\u20131298. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126381"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Vogel, C., Schindler, K., Roth, S.: Piecewise rigid scene flow. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1377\u20131384 (2013)","DOI":"10.1109\/ICCV.2013.174"},{"key":"14_CR39","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=uXl3bZLkr3c"},{"key":"14_CR40","unstructured":"Wang, J.K., Wibisono, A.: Towards understanding gd with hard and conjugate pseudo-labels for test-time adaptation. arXiv preprint arXiv:2210.10019 (2022)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Q., Fink, O., Van\u00a0Gool, L., Dai, D.: Continual test-time domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7201\u20137211 (2022)","DOI":"10.1109\/CVPR52688.2022.00706"},{"issue":"1","key":"14_CR42","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TIT.1974.1055171","volume":"20","author":"A Wyner","year":"1974","unstructured":"Wyner, A.: Recent results in the shannon theory. IEEE Trans. Inf. Theory 20(1), 2\u201310 (1974)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"14_CR43","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Xing, B., Ying, X., Wang, R., Yang, J., Chen, T.: Cross-modal contrastive learning for domain adaptation in 3d semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 2974\u20132982 (2023)","DOI":"10.1609\/aaai.v37i3.25400"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Int: towards infinite-frames 3d detection with an efficient framework. In: European Conference on Computer Vision, pp. 193\u2013209. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_12"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Yin, P., et al.: Outram: one-shot global localization via triangulated scene graph and global outlier pruning. arXiv preprint arXiv:2309.08914 (2023)","DOI":"10.1109\/ICRA57147.2024.10610206"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, L., Xie, B., Li, S.: Robust test-time adaptation in dynamic scenarios. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15922\u201315932 (2023)","DOI":"10.1109\/CVPR52729.2023.01528"},{"key":"14_CR48","first-page":"38629","volume":"35","author":"M Zhang","year":"2022","unstructured":"Zhang, M., Levine, S., Finn, C.: Memo: Test time robustness via adaptation and augmentation. Adv. Neural. Inf. Process. Syst. 35, 38629\u201338642 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"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\/978-3-031-73390-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:34:24Z","timestamp":1730306064000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}