{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T07:46:28Z","timestamp":1775461588670,"version":"3.50.1"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197680","type":"print"},{"value":"9783031197697","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\/978-3-031-19769-7_18","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T11:40:06Z","timestamp":1666438806000},"page":"304-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Towards Comprehensive Representation Enhancement in\u00a0Semantics-Guided Self-supervised Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Jingyuan","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"18_CR1","unstructured":"Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M.M., Reid, I.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"18_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"18_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"18_CR4","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Liu, A.H., Liu, Y.C., Wang, Y.C.F.: Towards scene understanding: unsupervised monocular depth estimation with semantic-aware representation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2619\u20132627 (2019)","DOI":"10.1109\/CVPR.2019.00273"},{"key":"18_CR6","unstructured":"Choi, J., Jung, D., Lee, D., Kim, C.: Safenet: self-supervised monocular depth estimation with semantic-aware feature extraction. In: Thirty-fourth Conference on Neural Information Processing Systems, NIPS 2020. NeurIPS (2020)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Choy, C., Park, J., Koltun, V.: Fully convolutional geometric features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8958\u20138966 (2019)","DOI":"10.1109\/ICCV.2019.00905"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"18_CR10","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"issue":"3","key":"18_CR11","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2017","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 611\u2013625 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Farooq Bhat, S., Alhashim, I., Wonka, P.: Adabins: depth estimation using adaptive bins. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4008\u20134017 (2021)","DOI":"10.1109\/CVPR46437.2021.00400"},{"issue":"2","key":"18_CR13","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/0304-3975(94)00262-2","volume":"154","author":"C Fiorio","year":"1996","unstructured":"Fiorio, C., Gustedt, J.: Two linear time union-find strategies for image processing. Theoret. Comput. Sci. 154(2), 165\u2013181 (1996)","journal-title":"Theoret. Comput. Sci."},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"18_CR15","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":"18_CR16","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Firman, M., Brostow, G.: Digging into self-supervised monocular depth estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3827\u20133837 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Goel, K., Srinivasan, P., Tariq, S., Philbin, J.: Quadronet: Multi-task learning for real-time semantic depth aware instance segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 315\u2013324, January 2021","DOI":"10.1109\/WACV48630.2021.00036"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. In: International Conference on Learning Representations (ICLR), April 2020","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 1\u20131 (2022)","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Lu, J., Tan, Y.P.: Discriminative deep metric learning for face verification in the wild. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1875\u20131882 (2014)","DOI":"10.1109\/CVPR.2014.242"},{"issue":"24","key":"18_CR24","doi-asserted-by":"publisher","first-page":"27225","DOI":"10.1109\/JSEN.2021.3109266","volume":"21","author":"H Jiang","year":"2021","unstructured":"Jiang, H., Ding, L., Sun, Z., Huang, R.: Unsupervised monocular depth perception: focusing on moving objects. IEEE Sens. J. 21(24), 27225\u201327237 (2021)","journal-title":"IEEE Sens. J."},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Jung, H., Park, E., Yoo, S.: Fine-grained semantics-aware representation enhancement for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12642\u201312652, October 2021","DOI":"10.1109\/ICCV48922.2021.01241"},{"key":"18_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-030-58565-5_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Klingner","year":"2020","unstructured":"Klingner, M., Term\u00f6hlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 582\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35"},{"issue":"4","key":"18_CR28","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1561\/2200000019","volume":"5","author":"B Kulis","year":"2012","unstructured":"Kulis, B.: Metric learning: a survey. Found. TrendsR Mach. Learn. 5(4), 287\u2013364 (2012). https:\/\/doi.org\/10.1561\/2200000019","journal-title":"Found. TrendsR Mach. Learn."},{"key":"18_CR29","unstructured":"Lee, J.H., Han, M.K., Ko, D.W., Suh, I.H.: From big to small: multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Lee, S., Im, S., Lin, S., Kweon, I.S.: Learning monocular depth in dynamic scenes via instance-aware projection consistency. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2021)","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"18_CR31","unstructured":"Li, R., et al.: Learning depth via leveraging semantics: self-supervised monocular depth estimation with both implicit and explicit semantic guidance (2021)"},{"key":"18_CR32","unstructured":"Li, R., et al.: Semantic-guided representation enhancement for self-supervised monocular trained depth estimation (2020)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR34","unstructured":"Lyu, X., et al.: HR-depth: High resolution self-supervised monocular depth estimation. arXiv preprint arXiv:2012.07356 6 (2020)"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"issue":"5","key":"18_CR36","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tard\u00f3s, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"18_CR37","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"issue":"4","key":"18_CR38","doi-asserted-by":"publisher","first-page":"6813","DOI":"10.1109\/LRA.2020.3017478","volume":"5","author":"V Patil","year":"2020","unstructured":"Patil, V., Van Gansbeke, W., Dai, D., Van Gool, L.: Don\u2019t forget the past: recurrent depth estimation from monocular video. IEEE Robot. Autom. Lett. 5(4), 6813\u20136820 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR39","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.robot.2017.03.019","volume":"93","author":"T Pire","year":"2017","unstructured":"Pire, T., Fischer, T., Castro, G., De Crist\u00f3foris, P., Civera, J., Jacobo Berlles, J.: S-PTAM: stereo parallel tracking and mapping. Robot. Auton. Syst. (RAS) 93, 27\u201342 (2017)","journal-title":"Robot. Auton. Syst. (RAS)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Poggi, M., Aleotti, F., Tosi, F., Mattoccia, S.: On the uncertainty of self-supervised monocular depth estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3224\u20133234 (2020)","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"18_CR41","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intelligence (TPAMI) 44, 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intelligence (TPAMI)"},{"key":"18_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1007\/978-3-030-58529-7_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Shu","year":"2020","unstructured":"Shu, C., Yu, K., Duan, Z., Yang, K.: Feature-metric loss for self-supervised learning of depth and egomotion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 572\u2013588. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_34"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., Moreno-Noguer, F.: Discriminative learning of deep convolutional feature point descriptors. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 118\u2013126 (2015)","DOI":"10.1109\/ICCV.2015.22"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Song, H.O., Jegelka, S., Rathod, V., Murphy, K.: Deep metric learning via facility location. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2206\u20132214 (2017)","DOI":"10.1109\/CVPR.2017.237"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.M.: Rethinking transformer-based set prediction for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3611\u20133620 (2021)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"18_CR46","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS 2017, Red Hook, NY, USA, pp. 6000\u20136010. Curran Associates Inc. (2017)"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Wang, C., Buenaposada, J.M., Zhu, R., Lucey, S.: Learning depth from monocular videos using direct methods. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2022\u20132030 (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhou, F., Wen, S., Liu, X., Lin, Y.: Deep metric learning with angular loss. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.283"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Wang, L., Wang, Y., Wang, L., Zhan, Y., Wang, Y., Lu, H.: Can scale-consistent monocular depth be learned in a self-supervised scale-invariant manner? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 12727\u201312736 (October 2021)","DOI":"10.1109\/ICCV48922.2021.01249"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"issue":"4","key":"18_CR51","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Watson, J., Mac Aodha, O., Prisacariu, V., Brostow, G., Firman, M.: The temporal opportunist: self-supervised multi-frame monocular depth. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1164\u20131174 (2021)","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Wu, K., Otoo, E., Shoshani, A.: Optimizing connected component labeling algorithms. In: Medical Imaging 2005: Image Processing, vol. 5747, pp. 1965\u20131976. SPIE (2005)","DOI":"10.1117\/12.596105"},{"key":"18_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46466-4_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"KM Yi","year":"2016","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467\u2013483. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_28"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 636\u2013644 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Zhan, H., Garg, R., Weerasekera, C.S., Li, K., Agarwal, H., Reid, I.M.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 340\u2013349 (2018)","DOI":"10.1109\/CVPR.2018.00043"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J., Koltun, V.: Exploring self-attention for image recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Shu, Y., Liu, Y.J.: Towards better generalization: joint depth-pose learning without posenet. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"18_CR60","unstructured":"Zheng, M., et al.: End-to-end object detection with adaptive clustering transformer. arXiv preprint arXiv:2011.09315 (2020)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"18_CR62","unstructured":"Zhou, H., Greenwood, D., Taylor, S.: Self-supervised monocular depth estimation with internal feature fusion. In: British Machine Vision Conference (BMVC) (2021)"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612\u20136619 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Fan, X., Shi, P., Xin, Y.: R-MSFM: Recurrent multi-scale feature modulation for monocular depth estimating. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 12777\u201312786 (October 2021)","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8848\u20138857 (2019)","DOI":"10.1109\/CVPR.2019.00906"},{"key":"18_CR66","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01228-1_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zou","year":"2018","unstructured":"Zou, Y., Luo, Z., Huang, J.-B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 38\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_3"}],"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\/978-3-031-19769-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:03:24Z","timestamp":1710338604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19769-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197680","9783031197697"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19769-7_18","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":"23 October 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)"}}]}}