{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:00:30Z","timestamp":1786978830604,"version":"3.56.0"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","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\/978-3-031-20077-9_39","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T12:21:52Z","timestamp":1667650912000},"page":"664-683","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["DEVIANT: Depth EquiVarIAnt NeTwork for\u00a0Monocular 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Abhinav","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garrick","family":"Brazil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique","family":"Corona","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Parchami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"39_CR1","unstructured":"The KITTI Vision Benchmark Suite. https:\/\/www.cvlibs.net\/datasets\/kitti\/eval_object.php?obj_benchmark=3d. Accessed 03 July 2022"},{"key":"39_CR2","unstructured":"Alhaija, H., Mustikovela, S., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets computer vision: efficient data generation for urban driving scenes. IJCV (2018)"},{"key":"39_CR3","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M$$3$$D-RPN: monocular $$3$$D region proposal network for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic $$3$$D object detection in monocular video. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"39_CR6","unstructured":"Bronstein, M.: Convolution from first principles. htpps:\/\/towardsdatascience.com\/deriving-convolution-from-first-principles-4ff124888028. Accessed 13 Aug 2021"},{"key":"39_CR7","unstructured":"Bronstein, M., Bruna, J., Cohen, T., Veli\u010dkovi\u0107, P.: Geometric deep learning: gGrids, groups, graphs, geodesics, and gauges. arXiv preprint arXiv:2104.13478 (2021)"},{"key":"39_CR8","unstructured":"Burns, B., Weiss, R., Riseman, E.: The non-existence of general-case view-invariants. In: Geometric Invariance in Computer Vision (1992)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Chabot, F., Chaouch, M., Rabarisoa, J., Teuliere, C., Chateau, T.: Deep MANTA: a coarse-to-fine many-task network for joint $$2$$D and $$3$$D vehicle analysis from monocular image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.198"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular $$3$$D object detection for autonomous driving. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"39_CR12","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A., Ma, H., Fidler, S., Urtasun, R.: $$3$$D object proposals for accurate object class detection. In: NeurIPS (2015)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: MonoPair: Monocular $$3$$D object detection using pairwise spatial relationships. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"39_CR14","unstructured":"Chong, Z., et al.: MonoDistill: learning spatial features for monocular $$3$$D object detection. In: ICLR (2022)"},{"key":"39_CR15","unstructured":"Cohen, T., Geiger, M., K\u00f6hler, J., Welling, M.: Spherical CNNs. In: ICLR (2018)"},{"key":"39_CR16","unstructured":"Cohen, T., Welling, M.: Learning the irreducible representations of commutative lie groups. In: ICML (2014)"},{"key":"39_CR17","unstructured":"Cohen, T., Welling, M.: Group equivariant convolutional networks. In: ICML (2016)"},{"key":"39_CR18","unstructured":"Dieleman, S., De Fauw, J., Kavukcuoglu, K.: Exploiting cyclic symmetry in convolutional neural networks. In: ICML (2016)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Ding, M., Huo, Y., Yi, H., Wang, Z., Shi, J., Lu, Z., Luo, P.: Learning depth-guided convolutions for monocular $$3$$D object detection. In: CVPR Workshops (2020)","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"39_CR20","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"39_CR21","unstructured":"Esteves, C., Allen-Blanchette, C., Zhou, X., Daniilidis, K.: Polar transformer networks. In: ICLR (2018)"},{"key":"39_CR22","unstructured":"Fidler, S., Dickinson, S., Urtasun, R.: $$3$$D object detection and viewpoint estimation with a deformable $$3$$D cuboid model. In: NeurIPS (2012)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Freeman, W., Adelson, E.: The design and use of steerable filters. TPAMI (1991)","DOI":"10.1109\/34.93808"},{"key":"39_CR24","unstructured":"Gandikota, K., Geiping, J., L\u00e4hner, Z., Czapli\u0144ski, A., Moeller, M.: Training or architecture? how to incorporate invariance in neural networks. arXiv preprint arXiv:2106.10044 (2021)"},{"key":"39_CR25","unstructured":"Ganea, O.E., B\u00e9cigneul, G., Hofmann, T.: Hyperbolic neural networks. In: NeurIPS (2017)"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"39_CR27","unstructured":"Ghosh, R., Gupta, A.: Scale steerable filters for locally scale-invariant convolutional neural networks. In: ICML Workshops (2019)"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"39_CR29","unstructured":"Henriques, J., Vedaldi, A.: Warped convolutions: Efficient invariance to spatial transformations. In: ICML (2017)"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Jansson, Y., Lindeberg, T.: Scale-invariant scale-channel networks: deep networks that generalise to previously unseen scales. IJCV (2021)","DOI":"10.1007\/s10851-022-01082-2"},{"key":"39_CR31","unstructured":"Jing, L.: Physical symmetry enhanced neural networks. Ph.D. thesis, Massachusetts Institute of Technology (2020)"},{"key":"39_CR32","unstructured":"Kanazawa, A., Sharma, A., Jacobs, D.: Locally scale-invariant convolutional neural networks. In: NeurIPS Workshops (2014)"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Kumar, A., Brazil, G., Liu, X.: GrooMeD-NMS: grouped mathematically differentiable NMS for monocular $$3$$D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: LUVLi face alignment: estimating landmarks\u2019 location, uncertainty, and visibility likelihood. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00826"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Kumar, A., Prabhakaran, V.: Estimation of bandlimited signals from the signs of noisy samples. In: ICASSP (2013)","DOI":"10.1109\/ICASSP.2013.6638779"},{"key":"39_CR36","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE (1998)","DOI":"10.1109\/5.726791"},{"key":"39_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/978-3-030-58580-8_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Li","year":"2020","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3d\u00a0detection from object keypoints for\u00a0autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 644\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_38"},{"key":"39_CR38","unstructured":"Lian, Q., Ye, B., Xu, R., Yao, W., Zhang, T.: Geometry-aware data augmentation for monocular $$3$$D object detection. arXiv preprint arXiv:2104.05858 (2021)"},{"key":"39_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Liu, L., Lu, J., Xu, C., Tian, Q., Zhou, J.: Deep fitting degree scoring network for monocular $$3$$D object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00115"},{"key":"39_CR41","doi-asserted-by":"crossref","unstructured":"Liu, X., Xue, N., Wu, T.: Learning auxiliary monocular contexts helps monocular $$3$$D object detection. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"39_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yixuan, Y., Liu, M.: Ground-aware monocular $$3$$D object detection for autonomous driving. Robotics and Automation Letters (2021)","DOI":"10.1109\/LRA.2021.3052442"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, D., Lu, F., Fang, J., Zhang, L.: AutoShape: real-time shape-aware monocular $$3$$D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"39_CR44","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular $$3$$D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"39_CR45","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":"39_CR46","unstructured":"Ma, X., Ouyang, W., Simonelli, A., Ricci, E.: $$3$$D object detection from images for autonomous driving: a survey. arXiv preprint arXiv:2202.02980 (2022)"},{"key":"39_CR47","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., Fan, X.: Accurate monocular $$3$$D object detection via color-embedded $$3$$D reconstruction for autonomous driving. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"key":"39_CR48","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular $$3$$D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"39_CR49","unstructured":"Marcos, D., Kellenberger, B., Lobry, S., Tuia, D.: Scale equivariance in CNNs with vector fields. In: ICML Workshops (2018)"},{"key":"39_CR50","doi-asserted-by":"crossref","unstructured":"Marcos, D., Volpi, M., Komodakis, N., Tuia, D.: Rotation equivariant vector field networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.540"},{"key":"39_CR51","doi-asserted-by":"crossref","unstructured":"Micheli, A.: Neural network for graphs: a contextual constructive approach. IEEE Trans. Neural Networks (2009)","DOI":"10.1109\/TNN.2008.2010350"},{"key":"39_CR52","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is Pseudo-LiDAR needed for monocular $$3$$D object detection? In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"39_CR53","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"39_CR54","doi-asserted-by":"crossref","unstructured":"Payet, N., Todorovic, S.: From contours to $$3$$D object detection and pose estimation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126342"},{"key":"39_CR55","doi-asserted-by":"crossref","unstructured":"Pepik, B., Stark, M., Gehler, P., Schiele, B.: Multi-view and $$3$$D deformable part models. TPAMI (2015)","DOI":"10.1109\/TPAMI.2015.2408347"},{"key":"39_CR56","unstructured":"Rath, M., Condurache, A.: Boosting deep neural networks with geometrical prior knowledge: a survey. arXiv preprint arXiv:2006.16867 (2020)"},{"key":"39_CR57","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.: Categorical depth distribution network for monocular $$3$$D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"39_CR58","doi-asserted-by":"crossref","unstructured":"Rematas, K., Kemelmacher-Shlizerman, I., Curless, B., Seitz, S.: Soccer on your tabletop. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00498"},{"key":"39_CR59","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"39_CR60","doi-asserted-by":"crossref","unstructured":"Saxena, A., Driemeyer, J., Ng, A.: Robotic grasping of novel objects using vision. IJRR (2008)","DOI":"10.1177\/0278364907087172"},{"key":"39_CR61","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: $$3$$D object proposal generation and detection from point cloud. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"39_CR62","doi-asserted-by":"crossref","unstructured":"Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., Kim, T.K.: Geometry-based distance decomposition for monocular $$3$$D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"39_CR63","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S., Porzi, L., Antequera, M., Kontschieder, P.: Disentangling monocular $$3$$D object detection: from single to multi-class recognition. TPAMI (2020)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"39_CR64","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S., Porzi, L., Kontschieder, P., Ricci, E.: Are we missing confidence in Pseudo-LiDAR methods for monocular $$3$$D object detection? In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00321"},{"key":"39_CR65","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular $$3$$D object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"39_CR66","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S., Porzi, L., Ricci, E., Kontschieder, P.: Towards generalization across depth for monocular $$3$$D object detection. In: ECCV (2020)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"39_CR67","unstructured":"Sosnovik, I., Moskalev, A., Smeulders, A.: DISCO: accurate discrete scale convolutions. In: BMVC (2021)"},{"key":"39_CR68","doi-asserted-by":"crossref","unstructured":"Sosnovik, I., Moskalev, A., Smeulders, A.: Scale equivariance improves siamese tracking. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00281"},{"key":"39_CR69","unstructured":"Sosnovik, I., Szmaja, M., Smeulders, A.: Scale-equivariant steerable networks. In: ICLR (2020)"},{"key":"39_CR70","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"39_CR71","doi-asserted-by":"crossref","unstructured":"Tang, Y., Dorn, S., Savani, C.: Center$$3$$D: center-based monocular $$3$$D object detection with joint depth understanding. arXiv preprint arXiv:2005.13423 (2020)","DOI":"10.1007\/978-3-030-71278-5_21"},{"key":"39_CR72","unstructured":"Thayalan-Vaz, S., M, S., Santhakumar, K., Ravi Kiran, B., Gauthier, T., Yogamani, S.: Exploring $$2$$D data augmentation for $$3$$D monocular object detection. arXiv preprint arXiv:2104.10786 (2021)"},{"key":"39_CR73","unstructured":"Thomas, N., Smidt, T., Kearnes, S., Yang, L., Li, L., Kohlhoff, K., Riley, P.: Tensor field networks: rotation-and translation-equivariant neural networks for $$3$$D point clouds. arXiv preprint arXiv:1802.08219 (2018)"},{"key":"39_CR74","doi-asserted-by":"crossref","unstructured":"Wang, L., Du, L., Ye, X., Fu, Y., Guo, G., Xue, X., Feng, J., Zhang, L.: Depth-conditioned dynamic message propagation for monocular $$3$$D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"39_CR75","unstructured":"Wang, L., Zhang, L., Zhu, Y., Zhang, Z., He, T., Li, M., Xue, X.: Progressive coordinate transforms for monocular $$3$$D object detection. In: NeurIPS (2021)"},{"key":"39_CR76","unstructured":"Wang, R., Walters, R., Yu, R.: Incorporating symmetry into deep dynamics models for improved generalization. In: ICLR (2021)"},{"key":"39_CR77","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.: Pseudo-LiDAR from visual depth estimation: bridging the gap in $$3$$D object detection for autonomous driving. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"39_CR78","unstructured":"Wang, Y., Guizilini, V., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: $$3$$D object detection from multi-view images via $$3$$D-to-$$2$$D queries. In: CoRL (2021)"},{"key":"39_CR79","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. TIP (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"39_CR80","unstructured":"Weiler, M., Forr\u00e9, P., Verlinde, E., Welling, M.: Coordinate independent convolutional networks-isometry and gauge equivariant convolutions on riemannian manifolds. arXiv preprint arXiv:2106.06020 (2021)"},{"key":"39_CR81","doi-asserted-by":"crossref","unstructured":"Weiler, M., Hamprecht, F., Storath, M.: Learning steerable filters for rotation equivariant CNNs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00095"},{"key":"39_CR82","unstructured":"Wilk, M.v.d., Bauer, M., John, S., Hensman, J.: Learning invariances using the marginal likelihood. In: NeurIPS (2018)"},{"key":"39_CR83","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/978-3-030-01228-1_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Worrall","year":"2018","unstructured":"Worrall, D., Brostow, G.: CubeNet: equivariance to 3D rotation and translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 585\u2013602. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_35"},{"key":"39_CR84","doi-asserted-by":"crossref","unstructured":"Worrall, D., Garbin, S., Turmukhambetov, D., Brostow, G.: Harmonic networks: deep translation and rotation equivariance. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.758"},{"key":"39_CR85","unstructured":"Worrall, D., Welling, M.: Deep scale-spaces: equivariance over scale. In: NeurIPS (2019)"},{"key":"39_CR86","unstructured":"Xu, Y., Xiao, T., Zhang, J., Yang, K., Zhang, Z.: Scale-invariant convolutional neural networks. arXiv preprint arXiv:1411.6369 (2014)"},{"key":"39_CR87","doi-asserted-by":"crossref","unstructured":"Yang, G., Ramanan, D.: Upgrading optical flow to $$3$$D scene flow through optical expansion. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00141"},{"key":"39_CR88","unstructured":"Yeh, R., Hu, Y.T., Schwing, A.: Chirality nets for human pose regression. NeurIPS (2019)"},{"key":"39_CR89","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2015)"},{"key":"39_CR90","unstructured":"Zhang, Y., Ma, X., Yi, S., Hou, J., Wang, Z., Ouyang, W., Xu, D.: Learning geometry-guided depth via projective modeling for monocular $$3$$D object detection. arXiv preprint arXiv:2107.13931 (2021)"},{"key":"39_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular $$3$$D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"39_CR92","unstructured":"Zhou, A., Knowles, T., Finn, C.: Meta-learning symmetries by reparameterization. In: ICLR (2021)"},{"key":"39_CR93","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"39_CR94","doi-asserted-by":"crossref","unstructured":"Zhou, Y., He, Y., Zhu, H., Wang, C., Li, H., Jiang, Q.: MonoEF: extrinsic parameter free monocular $$3$$D object detection. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3136899"},{"key":"39_CR95","unstructured":"Zhu, W., Qiu, Q., Calderbank, R., Sapiro, G., Cheng, X.: Scale-equivariant neural networks with decomposed convolutional filters. arXiv preprint arXiv:1909.11193 (2019)"},{"key":"39_CR96","doi-asserted-by":"crossref","unstructured":"Zou, Z., et al.: The devil is in the task: exploiting reciprocal appearance-localization features for monocular $$3$$D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00271"},{"key":"39_CR97","doi-asserted-by":"crossref","unstructured":"Zwicke, P., Kiss, I.: A new implementation of the mellin transform and its application to radar classification of ships. TPAMI (1983)","DOI":"10.1109\/TPAMI.1983.4767371"}],"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\/978-3-031-20077-9_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T19:21:43Z","timestamp":1667848903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_39","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":"6 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)"}}]}}