{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:30:18Z","timestamp":1780511418583,"version":"3.54.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727832","type":"print"},{"value":"9783031727849","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72784-9_6","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"96-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["MonoTTA: Fully Test-Time Adaptation for Monocular 3D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4057-7360","authenticated-orcid":false,"given":"Hongbin","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-1074","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-1831","authenticated-orcid":false,"given":"Shuaicheng","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7669-2686","authenticated-orcid":false,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"6_CR1","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":"6_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"6_CR3","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: Monopair: monocular 3D object detection using pairwise spatial relationships. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12093\u201312102 (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: VoxelNeXt: fully sparse VoxelNet for 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21674\u201321683 (2023)","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Ding, M., et al.: Learning depth-guided convolutions for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1000\u20131001 (2020)","DOI":"10.1109\/CVPRW50498.2020.00508"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"6_CR8","unstructured":"Fleuret, F., et\u00a0al.: Test time adaptation through perturbation robustness. In: NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (2021)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hegde, D., Kilic, V., Sindagi, V., Cooper, A.B., Foster, M., Patel, V.M.: Source-free unsupervised domain adaptation for 3D object detection in adverse weather. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 6973\u20136980. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161341"},{"key":"6_CR11","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2018)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Hwang, I., Kim, Y.M.: Ev-TTA: test-time adaptation for event-based object recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17745\u201317754 (2022)","DOI":"10.1109\/CVPR52688.2022.01722"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Kim, Y., Yim, J., Yun, J., Kim, J.: NLNL: negative learning for noisy labels. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 101\u2013110 (2019)","DOI":"10.1109\/ICCV.2019.00019"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kim, Y., Yun, J., Shon, H., Kim, J.: Joint negative and positive learning for noisy labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9442\u20139451 (2021)","DOI":"10.1109\/CVPR46437.2021.00932"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Kumar, A., Brazil, G., Liu, X.: GrooMeD-NMS: grouped mathematically differentiable NMS for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8973\u20138983 (2021)","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, X., Shen, S.: Stereo R-CNN based 3D object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7644\u20137652 (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"6_CR17","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":"6_CR18","doi-asserted-by":"publisher","unstructured":"Lin, H., et al.: Prototype-guided continual adaptation for class-incremental unsupervised domain adaptation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 351\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_21","DOI":"10.1007\/978-3-031-19827-4_21"},{"key":"6_CR19","unstructured":"Liu, Y., Kothari, P., Van\u00a0Delft, B., Bellot-Gurlet, B., Mordan, T., Alahi, A.: TTT++: when does self-supervised test-time training fail or thrive? In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 21808\u201321820 (2021)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: SMOKE: single-stage monocular 3D object detection via keypoint estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: LATR: 3D lane detection from monocular images with transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7941\u20137952 (2023)","DOI":"10.1109\/ICCV51070.2023.00730"},{"key":"6_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58601-0_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Ma","year":"2020","unstructured":"Ma, X., Liu, S., Xia, Z., Zhang, H., Zeng, X., Ouyang, W.: Rethinking pseudo-LiDAR representation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 311\u2013327. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_19"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mirza, M.J., Soneira, P.J., Lin, W., Kozinski, M., Possegger, H., Bischof, H.: ActMAD: activation matching to align distributions for test-time-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24152\u201324161 (2023)","DOI":"10.1109\/CVPR52729.2023.02313"},{"key":"6_CR25","unstructured":"Nado, Z., Padhy, S., Sculley, D., D\u2019Amour, A., Lakshminarayanan, B., Snoek, J.: Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv:2006.10963 (2020)"},{"key":"6_CR26","unstructured":"Niu, S., et al.: Efficient test-time model adaptation without forgetting. In: The Internetional Conference on Machine Learning (2022)"},{"key":"6_CR27","unstructured":"Niu, S., et al.: Towards stable test-time adaptation in dynamic wild world. In: International Conference on Learning Representations (2023)"},{"key":"6_CR28","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Qin, Z., Li, X.: MonoGround: detecting monocular 3D objects from the ground. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3793\u20133802 (2022)","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Zhang, Y., Lin, H., et\u00a0al.: Source-free domain adaptation via avatar prototype generation and adaptation. In: International Joint Conference on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2021\/402"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Saltori, C., Lathuili\u00e9re, S., Sebe, N., Ricci, E., Galasso, F.: SF-UDA 3D: source-free unsupervised domain adaptation for lidar-based 3D object detection. In: 2020 International Conference on 3D Vision (3DV), pp. 771\u2013780. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00087"},{"key":"6_CR33","unstructured":"Schneider, S., Rusak, E., Eck, L., Bringmann, O., Brendel, W., Bethge, M.: Improving robustness against common corruptions by covariate shift adaptation. In: Advances in Neural Information Processing Systems, pp. 11539\u201311551 (2020)"},{"key":"6_CR34","unstructured":"Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A., Hardt, M.: Test-time training with self-supervision for generalization under distribution shifts. In: International Conference on Machine Learning, pp. 9229\u20139248. PMLR (2020)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Veksler, O.: Test time adaptation with regularized loss for weakly supervised salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7360\u20137369 (2023)","DOI":"10.1109\/CVPR52729.2023.00711"},{"key":"6_CR36","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization. In: The International Conference on Machine Learning (2021)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-LiDAR from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8445\u20138453 (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., Wen, C., Shi, S., Li, X., Wang, C.: Virtual sparse convolution for multimodal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21653\u201321662 (2023)","DOI":"10.1109\/CVPR52729.2023.02074"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2345\u20132353 (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: MonoNeRD: NeRF-like representations for monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6814\u20136824 (2023)","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Yang, J., Shi, S., Wang, Z., Li, H., Qi, X.: ST3D: self-training for unsupervised domain adaptation on 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10368\u201310378 (2021)","DOI":"10.1109\/CVPR46437.2021.01023"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Ye, X., et al.: Rope3D: the roadside perception dataset for autonomous driving and monocular 3D object detection task. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21341\u201321350 (2022)","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"6_CR43","unstructured":"Zhang, M., Levine, S., Finn, C.: MEMO: test time robustness via adaptation and augmentation. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 38629\u201338642 (2022)"},{"key":"6_CR44","unstructured":"Zhang, Y., Hooi, B., Hong, L., Feng, J.: Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 34077\u201334090 (2022)"},{"key":"6_CR45","unstructured":"Zhang, Y., Hooi, B., Hu, D., Liang, J., Feng, J.: Unleashing the power of contrastive self-supervised visual models via contrast-regularized fine-tuning. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 29848\u201329860 (2021)"},{"issue":"9","key":"6_CR46","doi-asserted-by":"publisher","first-page":"10795","DOI":"10.1109\/TPAMI.2023.3268118","volume":"45","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Kang, B., Hooi, B., Yan, S., Feng, J.: Deep long-tailed learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10795\u201310816 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR47","doi-asserted-by":"publisher","first-page":"7834","DOI":"10.1109\/TIP.2020.3006377","volume":"29","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., et al.: Collaborative unsupervised domain adaptation for medical image diagnosis. IEEE Trans. Image Process. 29, 7834\u20137844 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133298 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Zou, Z., et al.: The devil is in the task: exploiting reciprocal appearance-localization features for monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2713\u20132722 (2021)","DOI":"10.1109\/ICCV48922.2021.00271"}],"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\/978-3-031-72784-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:47:20Z","timestamp":1727596040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72784-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727832","9783031727849"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72784-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}