{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:58:35Z","timestamp":1776441515293,"version":"3.51.2"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250620","type":"print"},{"value":"9783031250637","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25063-7_19","type":"book-chapter","created":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T20:10:15Z","timestamp":1676491815000},"page":"308-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Hybrid Transformer Based Feature Fusion for\u00a0Self-Supervised Monocular Depth Estimation"],"prefix":"10.1007","author":[{"given":"Snehal Singh","family":"Tomar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maitreya","family":"Suin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. N.","family":"Rajagopalan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"19_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: AdaBins: depth estimation using adaptive bins. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4009\u20134018 (2021)"},{"key":"19_CR2","unstructured":"Bian, J., et al.: Unsupervised scale-consistent depth and ego-motion learning from monocular video. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/6364d3f0f495b6ab9dcf8d3b5c6e0b01-Paper.pdf"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4985\u20134995 (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"19_CR4","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. CoRR abs\/1811.06152 (2018). http:\/\/arxiv.org\/abs\/1811.06152"},{"key":"19_CR5","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2019.00273","DOI":"10.1109\/CVPR.2019.00273"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"key":"19_CR7","doi-asserted-by":"publisher","unstructured":"Choi, J., Jung, D., Lee, D., Kim, C.: SAFENet: self-supervised monocular depth estimation with semantic-aware feature extraction (2020). https:\/\/doi.org\/10.48550\/ARXIV.2010.02893. https:\/\/arxiv.org\/abs\/2010.02893","DOI":"10.48550\/ARXIV.2010.02893"},{"key":"19_CR8","unstructured":"Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. In: International Conference on Machine Learning, pp. 933\u2013941. PMLR (2017)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Q., Cao, C., Fu, Y.: Incremental transformer structure enhanced image inpainting with masking positional encoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11358\u201311368 (2022)","DOI":"10.1109\/CVPR52688.2022.01107"},{"key":"19_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"19_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"19_CR12","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/7bccfde7714a1ebadf06c5f4cea752c1-Paper.pdf"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D.: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"19_CR14","unstructured":"Gao, F., Yu, J., Shen, H., Wang, Y., Yang, H.: Attentional separation-and-aggregation network for self-supervised depth-pose learning in dynamic scenes. CoRR abs\/2011.09369 (2020). https:\/\/arxiv.org\/abs\/2011.09369"},{"key":"19_CR15","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: Unsupervised monocular depth learning from unknown cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Multi-scale high-resolution vision transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12094\u201312103 (2022)","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"19_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"19_CR20","unstructured":"Guizilini, V., Hou, R., Li, J., Ambrus, R., Gaidon, A.: Semantically-guided representation learning for self-supervised monocular depth. CoRR abs\/2002.12319 (2020). https:\/\/arxiv.org\/abs\/2002.12319"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: a set-to-set approach to 3D object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8417\u20138427 (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"19_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 (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR23","doi-asserted-by":"publisher","unstructured":"He, L., Lu, J., Wang, G., Song, S., Zhou, J.: SOSD-Net: joint semantic object segmentation and depth estimation from monocular images. Neurocomputing 440, 251\u2013263 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.01.126. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231221002344","DOI":"10.1016\/j.neucom.2021.01.126"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Huynh, L., Nguyen, P., Matas, J., Rahtu, E., Heikkil\u00e4, J.: Boosting monocular depth estimation with lightweight 3D point fusion. CoRR abs\/2012.10296 (2020). https:\/\/arxiv.org\/abs\/2012.10296","DOI":"10.1109\/ICCV48922.2021.01253"},{"key":"19_CR25","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Johnston, A., Carneiro, G.: Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"19_CR27","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https:\/\/doi.org\/10.48550\/ARXIV.1412.6980. https:\/\/arxiv.org\/abs\/1412.6980","DOI":"10.48550\/ARXIV.1412.6980"},{"key":"19_CR28","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"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Kopf, J., Rong, X., Huang, J.B.: Robust consistent video depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1611\u20131621 (2021)","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Klingner, M., Yogamani, S., Milz, S., Fingscheidt, T., Mader, P.: SynDistNet: self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 61\u201371 (2021)","DOI":"10.1109\/WACV48630.2021.00011"},{"key":"19_CR31","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. Proceed. AAAI Conf. Artif. Intell. 35(3), 1863\u20131872 (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16281","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Li, S., Xue, F., Wang, X., Yan, Z., Zha, H.: Sequential adversarial learning for self-supervised deep visual odometry. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00294"},{"key":"19_CR33","unstructured":"Li, Z.: Monocular depth estimation toolbox. https:\/\/github.com\/zhyever\/Monocular-Depth-Estimation-Toolbox (2022)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R.: SwinIR: image restoration using swin transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1833\u20131844 (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"issue":"10","key":"19_CR35","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2019.2930258","volume":"42","author":"C Luo","year":"2020","unstructured":"Luo, C., et al.: Every pixel counts ++: joint learning of geometry and motion with 3D holistic understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2624\u20132641 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2930258","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"19_CR37","doi-asserted-by":"publisher","unstructured":"Naderi, T., Sadovnik, A., Hayward, J., Qi, H.: Monocular depth estimation with adaptive geometric attention. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 617\u2013627 (2022). https:\/\/doi.org\/10.1109\/WACV51458.2022.00069","DOI":"10.1109\/WACV51458.2022.00069"},{"key":"19_CR38","doi-asserted-by":"publisher","unstructured":"Patil, V., Sakaridis, C., Liniger, A., Van Gool, L.: P3Depth: monocular depth estimation with a piecewise planarity prior (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.02091. https:\/\/arxiv.org\/abs\/2204.02091","DOI":"10.48550\/ARXIV.2204.02091"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Pilzer, A., Lathuiliere, S., Sebe, N., Ricci, E.: Refine and distill: exploiting cycle-inconsistency and knowledge distillation for unsupervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01000"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Liu, Z., Urtasun, R., Jia, J.: GeoNet: geometric neural network for joint depth and surface normal estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"19_CR42","unstructured":"Ranjan, A., Jampani, V., Kim, K., Sun, D., Wulff, J., Black, M.J.: Adversarial collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. CoRR abs\/1805.09806 (2018). http:\/\/arxiv.org\/abs\/1805.09806"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Saeedan, F., Roth, S.: Boosting monocular depth with panoptic segmentation maps. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3853\u20133862 (2021)","DOI":"10.1109\/WACV48630.2021.00390"},{"key":"19_CR44","unstructured":"Saxena, A., Chung, S., Ng, A.: Learning depth from single monocular images. In: Weiss, Y., Sch\u00f6lkopf, B., Platt, J. (eds.) Advances in Neural Information Processing Systems, vol. 18. MIT Press (2005). https:\/\/proceedings.neurips.cc\/paper\/2005\/file\/17d8da815fa21c57af9829fb0a869602-Paper.pdf"},{"issue":"5","key":"19_CR45","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena, A., Sun, M., Ng, A.Y.: Make3D: Learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2009). https:\/\/doi.org\/10.1109\/TPAMI.2008.132","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Tosi, F., Aleotti, F., Ramirez, P.Z., Poggi, M., Salti, S., Stefano, L.D., Mattoccia, S.: Distilled semantics for comprehensive scene understanding from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00471"},{"key":"19_CR48","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"19_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"issue":"10","key":"19_CR50","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR51","doi-asserted-by":"publisher","unstructured":"Wang, L., Zhang, J., Wang, O., Lin, Z., Lu, H.: SDC-Depth: semantic divide-and-conquer network for monocular depth estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 538\u2013547 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00062","DOI":"10.1109\/CVPR42600.2020.00062"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: Uformer: A general u-shaped transformer for image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17683\u201317693 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"issue":"4","key":"19_CR53","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.C., Sheikh, H.R., Simoncelli, E.P.: 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":"19_CR54","doi-asserted-by":"publisher","unstructured":"Weder, S., Sch\u00f6nberger, J.L., Pollefeys, M., Oswald, M.R.: NeuralFusion: online depth fusion in latent space. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3161\u20133171 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00318","DOI":"10.1109\/CVPR46437.2021.00318"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Xian, K., Zhang, J., Wang, O., Mai, L., Lin, Z., Cao, Z.: Structure-guided ranking loss for single image depth prediction. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Xu, D.: Multi-class token transformer for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4310\u20134319 (2022)","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"19_CR58","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1109\/LSP.2021.3067498","volume":"28","author":"X Xu","year":"2021","unstructured":"Xu, X., Chen, Z., Yin, F.: Monocular depth estimation with multi-scale feature fusion. IEEE Signal Process. Lett. 28, 678\u2013682 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3067498","journal-title":"IEEE Signal Process. Lett."},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: DOLG: single-stage image retrieval with deep orthogonal fusion of local and global features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11772\u201311781 (2021)","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"19_CR60","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Restormer: efficient transformer for high-resolution image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728\u20135739 (2022)","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"19_CR62","doi-asserted-by":"publisher","unstructured":"Zhu, S., Brazil, G., Liu, X.: The edge of depth: explicit constraints between segmentation and depth. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13113\u201313122 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01313","DOI":"10.1109\/CVPR42600.2020.01313"},{"key":"19_CR63","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 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25063-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T19:05:51Z","timestamp":1710270351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25063-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250620","9783031250637"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25063-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"16 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}