{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T13:06:56Z","timestamp":1748092016018},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T00:00:00Z","timestamp":1585267200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T00:00:00Z","timestamp":1585267200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s11263-020-01323-0","type":"journal-article","created":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T11:02:46Z","timestamp":1585306966000},"page":"1331-1359","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image"],"prefix":"10.1007","volume":"128","author":[{"given":"Matthieu","family":"Grard","sequence":"first","affiliation":[]},{"given":"Emmanuel","family":"Dellandr\u00e9a","sequence":"additional","affiliation":[]},{"given":"Liming","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,27]]},"reference":[{"key":"1323_CR1","doi-asserted-by":"crossref","unstructured":"Antoniou, A., Storkey, A. J., & Edwards, H. (2018). Augmenting image classifiers using data augmentation generative adversarial networks. In International conference on artificial neural networks and machine learning (ICANN) (Vol. 11141, pp. 594\u2013603). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"1323_CR2","unstructured":"Ayvaci, A., Raptis, M., & Soatto, S. (2010). Occlusion detection and motion estimation with convex optimization. In Advances in neural information processing systems (NIPS) (pp. 100\u2013108)."},{"issue":"3","key":"1323_CR3","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/s11263-011-0490-7","volume":"97","author":"A Ayvaci","year":"2012","unstructured":"Ayvaci, A., Raptis, M., & Soatto, S. (2012). Sparse occlusion detection with optical flow. International Journal of Computer Vision (IJCV), 97(3), 322\u2013338.","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"12","key":"1323_CR4","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). SegNet: A deep convolutional encoder\u2013decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1323_CR5","doi-asserted-by":"crossref","unstructured":"Bai, M., Urtasun, R. (2017). Deep watershed transform for instance segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 2858\u20132866). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.305"},{"key":"1323_CR6","doi-asserted-by":"crossref","unstructured":"Batra, A., Singh, S., Pang, G., Basu, S., Jawahar, C., & Paluri, M. (2019). Improved road connectivity by joint learning of orientation and segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 10385\u201310393). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.01063"},{"issue":"1\u20132","key":"1323_CR7","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","volume":"79","author":"S Ben-David","year":"2010","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010a). A theory of learning from different domains. Machine Learning, 79(1\u20132), 151\u2013175.","journal-title":"Machine Learning"},{"key":"1323_CR8","unstructured":"Ben-David, S., Lu, T., Luu, T., P\u00e1l, D. (2010b). Impossibility theorems for domain adaptation. In International conference on artificial intelligence and statistics (AISTATS), JMLR.org, JMLR proceedings (Vol. 9, pp. 129\u2013136)."},{"key":"1323_CR9","unstructured":"Blender Online Community. (2016). Blender\u2014a 3D modelling and rendering package. Blender Foundation, Blender Institute, Amsterdam, http:\/\/www.blender.org."},{"key":"1323_CR10","doi-asserted-by":"crossref","unstructured":"Br\u00e9gier, R., Devernay, F., Leyrit, L., & Crowley, J. L. (2017). Symmetry aware evaluation of 3d object detection and pose estimation in scenes of many parts in bulk. In International conference on computer vision workshops (ICCVW) (pp. 2209\u20132218). IEEE Computer Society.","DOI":"10.1109\/ICCVW.2017.258"},{"key":"1323_CR11","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J. R. R., Ferrari, V. (2018). COCO-Stuff: Thing and stuff classes in context. In Conference on computer vision and pattern recognition (CVPR) (pp. 1209\u20131218). IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"1323_CR12","unstructured":"Cai, H., Zhu, L., & Han, S. (2019). ProxylessNAS: Direct neural architecture search on target task and hardware. In International conference on learning representations (ICLR)."},{"key":"1323_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder\u2013decoder with atrous separable convolution for semantic image segmentation. In European conference on computer vision (ECCV) part VII (Vol. 11211, pp. 833\u2013851). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1323_CR14","doi-asserted-by":"crossref","unstructured":"Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2019). AutoAugment: learning augmentation strategies from data. In Conference on computer vision and pattern recognition (CVPR) (pp. 113\u2013123). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.00020"},{"key":"1323_CR15","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Sun, J. (2016). Instance-aware semantic segmentation via multi-task network cascades. In Conference on computer vision and pattern recognition (CVPR) (pp. 3150\u20133158). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.343"},{"key":"1323_CR16","doi-asserted-by":"crossref","unstructured":"Deng, R., Shen, C., Liu, S., Wang, H., & Liu, X. (2018). Learning to predict crisp boundaries. In European conference on computer vision (ECCV) part VI (Vol. 11210, pp. 570\u2013586). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01231-1_35"},{"key":"1323_CR17","doi-asserted-by":"crossref","unstructured":"Do, T. T., Nguyen, A., & Reid, I. D. (2018). AffordanceNet: An end-to-end deep learning approach for object affordance detection. In International conference on robotics and automation (ICRA) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"1323_CR18","doi-asserted-by":"crossref","unstructured":"Dong, X., Yan, Y., Ouyang, W., Yang, Y. (2018). Style aggregated network for facial landmark detection. In Conference on computer vision and pattern recognition (CVPR) (pp. 379\u2013388). IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00047"},{"key":"1323_CR19","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In Advances in neural information processing systems (NIPS) (pp. 2366\u20132374)."},{"issue":"1","key":"1323_CR20","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. M., Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision (IJCV), 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1323_CR21","doi-asserted-by":"crossref","unstructured":"Fan, R., Cheng, M. M., Hou, Q., Mu, T. J., Wang, J., & Hu, S. M. (2019). S4Net: Single stage salient-instance segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 6103\u20136112). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.00626"},{"key":"1323_CR22","doi-asserted-by":"crossref","unstructured":"Follmann, P., B\u00f6ttger, T., H\u00e4rtinger, P., K\u00f6nig, R., & Ulrich, M. (2018). MVTec D2S: Densely segmented supermarket dataset. In European conference on computer vision (ECCV) part X (Vol. 11214, pp. 581\u2013597). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01249-6_35"},{"key":"1323_CR23","doi-asserted-by":"crossref","unstructured":"Follmann, P., K\u00f6nig, R., H\u00e4rtinger, P., Klostermann, M., & B\u00f6ttger, T. (2019). Learning to see the invisible: End-to-end trainable amodal instance segmentation. In Winter conference on applications of computer vision, (WACV) (pp. 1328\u20131336). IEEE.","DOI":"10.1109\/WACV.2019.00146"},{"key":"1323_CR24","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. (2018). Deep ordinal regression network for monocular depth estimation. In Conference on computer vision and pattern recognition (CVPR) (pp. 2002\u20132011). IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00214"},{"key":"1323_CR25","doi-asserted-by":"crossref","unstructured":"Fu, H., Wang, C., Tao, D., & Black, M. J. (2016). Occlusion boundary detection via deep exploration of context. In Conference on computer vision and pattern recognition (CVPR) (pp. 241\u2013250). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.33"},{"key":"1323_CR26","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. In Conference on computer vision and pattern recognition (CVPR), IEEE Computer Society."},{"key":"1323_CR27","doi-asserted-by":"crossref","unstructured":"Gan, Y., Xu, X., Sun, W., & Lin, L. (2018). Monocular depth estimation with affinity, vertical pooling, and label enhancement. In European conference on computer vision (ECCV) part III (Vol. 11207, pp. 232\u2013247). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01219-9_14"},{"issue":"11","key":"1323_CR28","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The KITTI dataset. International Journal of Robotics Research (IJRR), 32(11), 1231\u20131237.","journal-title":"International Journal of Robotics Research (IJRR)"},{"issue":"3","key":"1323_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/BF01679683","volume":"14","author":"D Geiger","year":"1995","unstructured":"Geiger, D., Ladendorf, B., & Yuille, A. L. (1995). Occlusions and binocular stereo. International Journal of Computer Vision (IJCV), 14(3), 211\u2013226.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1323_CR30","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In International conference on artificial intelligence and statistics (AISTATS), JMLR.org, JMLR proceedings (Vol. 9, pp. 249\u2013256)"},{"issue":"3","key":"1323_CR31","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/76.678630","volume":"8","author":"N Grammalidis","year":"1998","unstructured":"Grammalidis, N., & Strintzis, M. G. (1998). Disparity and occlusion estimation in multiocular systems and their coding for the communication of multiview image sequences. Transactions on Circuits and Systems for Video Technology (TCSVT), 8(3), 328\u2013344.","journal-title":"Transactions on Circuits and Systems for Video Technology (TCSVT)"},{"key":"1323_CR32","unstructured":"Grard, M., Br\u00e9gier, R., Sella, F., Dellandr\u00e9a, E., & Chen, L. (2018). Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network. In 2017 international workshop on human-friendly robotics (Vol. 7, pp. 207\u2013221). Springer proceedings in advanced robotics, Springer."},{"key":"1323_CR33","unstructured":"Guan, S., Khan, A. A., Sikdar, S., Chitnis, P. V. (2018). Fully dense UNet for 2D sparse photoacoustic tomography artifact removal. Journal of Biomedical and Health Informatics."},{"key":"1323_CR34","doi-asserted-by":"crossref","unstructured":"Hayder, Z., He, X., & Salzmann, M. (2017). Boundary-aware instance segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 587\u2013595). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.70"},{"key":"1323_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. B. (2017). Mask R-CNN. In International conference on computer vision (ICCV) (pp. 2980\u20132988). IEEE Computer Society.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1323_CR36","doi-asserted-by":"crossref","unstructured":"He, X., & Yuille, A. (2010). Occlusion boundary detection using pseudo-depth. In European conference on computer vision (ECCV) part IV (Vol. 6314, pp. 539\u2013552). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-642-15561-1_39"},{"key":"1323_CR37","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van\u00a0der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Conference on computer vision and pattern recognition (CVPR) (pp. 2261\u20132269). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1323_CR38","doi-asserted-by":"crossref","unstructured":"Humayun, A., Mac Aodha, O., Brostow, G. J. (2011). Learning to find occlusion regions. In Conference on computer vision and pattern recognition (CVPR) (pp. 2161\u20132168). IEEE Computer Society.","DOI":"10.1109\/CVPR.2011.5995517"},{"key":"1323_CR39","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. In International conference on multimedia (pp. 675\u2013678). ACM, MM\u201914.","DOI":"10.1145\/2647868.2654889"},{"key":"1323_CR40","unstructured":"Kendall, A., Gal, Y., & Cipolla, R. (2018). Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Conference on computer vision and pattern recognition (CVPR) (pp. 7482\u20137491). IEEE Computer Society."},{"key":"1323_CR41","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International conference on learning representations (ICLR)."},{"key":"1323_CR42","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Levinkov, E., Andres, B., Savchynskyy, B., & Rother, C. (2017). InstanceCut: From edges to instances with multicut. In Conference on computer vision and pattern recognition (CVPR) (pp. 7322\u20137331). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.774"},{"key":"1323_CR43","unstructured":"Kirillov, A., Wu, Y., He, K., & Girshick, R. B. (2019). PointRend: Image segmentation as rendering. CoRR, arXiv:1912.08193, http:\/\/arxiv.org\/abs\/1912.08193"},{"key":"1323_CR44","doi-asserted-by":"crossref","unstructured":"Kong, S., & Fowlkes, C. C. (2018). Recurrent pixel embedding for instance grouping. In Conference on computer vision and pattern recognition (CVPR) (pp. 9018\u20139028). IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00940"},{"key":"1323_CR45","doi-asserted-by":"crossref","unstructured":"Lee, W., Na, J., & Kim, G. (2019). Multi-task self-supervised object detection via recycling of bounding box annotations. In Conference on computer vision and pattern recognition (CVPR) (pp. 4984\u20134993). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.00512"},{"key":"1323_CR46","unstructured":"Li, B., Shen, C., Dai, Y., van\u00a0den Hengel, A., & He, M. (2015). Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In Conference on computer vision and pattern recognition (CVPR) (pp. 1119\u20131127). IEEE Computer Society."},{"key":"1323_CR47","doi-asserted-by":"crossref","unstructured":"Li, G., Xie, Y., Lin, L., & Yu, Y. (2017). Instance-level salient object segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 247\u2013256). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.34"},{"key":"1323_CR48","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R. B., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In International conference on computer vision (ICCV) (pp. 2999\u20133007). IEEE Computer Society.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1323_CR49","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In European conference on computer vision (ECCV) Part V (Vol. 8693, pp. 740\u2013755). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"10","key":"1323_CR50","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2016","unstructured":"Liu, F., Shen, C., Lin, G., & Reid, I. D. (2016). Learning depth from single monocular images using deep convolutional neural fields. IEEE Transactions on Pattern Analysis Machine Intelligence (TPAMI), 38(10), 2024\u20132039.","journal-title":"IEEE Transactions on Pattern Analysis Machine Intelligence (TPAMI)"},{"key":"1323_CR51","doi-asserted-by":"crossref","unstructured":"Liu, G., Si, J., Hu, Y., & Li, S. (2018a). Photographic image synthesis with improved U-net. In International conference on advanced computational intelligence (ICACI) (pp. 402\u2013407). IEEE.","DOI":"10.1109\/ICACI.2018.8377492"},{"key":"1323_CR52","unstructured":"Liu, R., Lehman, J., Molino, P., Such, F. P., Frank, E., Sergeev, A., & Yosinski, J. (2018b). An intriguing failing of convolutional neural networks and the coordconv solution. In Advances in neural information processing systems (NeurIPS) (pp. 9628\u20139639)."},{"key":"1323_CR53","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., & Davison, A. J. (2019). End-to-end multi-task learning with attention. In Conference on computer vision and pattern recognition (CVPR) (pp. 1871\u20131880). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.00197"},{"key":"1323_CR54","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018c). Path aggregation network for instance segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 8759\u20138768). IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1323_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cheng, M. M., Hu, X., Wang, K., & Bai, X. (2017). Richer convolutional features for edge detection. In Conference on computer vision and pattern recognition (CVPR) (pp. 5872\u20145881). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.622"},{"key":"1323_CR56","doi-asserted-by":"crossref","unstructured":"Luo, P., Wang, G., Lin, L., & Wang, X. (2017). Deep dual learning for semantic image segmentation. In International conference on computer vision (ICCV) (pp. 2737\u20132745). IEEE Computer Society.","DOI":"10.1109\/ICCV.2017.296"},{"key":"1323_CR57","doi-asserted-by":"crossref","unstructured":"Maninis, K. K., Pont-Tuset, J., Arbel\u00e1ez, P. A., & Gool, L. J. V. (2016). Convolutional oriented boundaries. In European conference on computer vision (ECCV) part I (Vol. 9905, pp. 580\u2013596). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-319-46448-0_35"},{"key":"1323_CR58","doi-asserted-by":"crossref","unstructured":"Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In International conference on computer vision (ICCV) (pp. 416\u2013423). IEEE Computer Society.","DOI":"10.1109\/ICCV.2001.937655"},{"key":"1323_CR59","unstructured":"McCormac, J., Handa, A., Leutenegger, S., & Davison, A. J. (2017). SceneNet RGB-D: Can 5M synthetic images beat generic imagenet pre-training on indoor segmentation? In International conference on computer vision (ICCV) (pp. 2697\u20132706). IEEE Computer Society."},{"key":"1323_CR60","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., & Hebert, M. (2016). Cross-stitch networks for multi-task learning. In Conference on computer vision and pattern recognition (CVPR) (pp. 3994\u20134003). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.433"},{"key":"1323_CR61","doi-asserted-by":"crossref","unstructured":"Novotn\u00fd, D., Albanie, S., Larlus, D., & Vedaldi, A. (2018). Semi-convolutional operators for instance segmentation. In European conference on computer vision (ECCV) part I (Vol. 11205, pp. 89\u2013105). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01246-5_6"},{"issue":"1","key":"1323_CR62","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2017","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J. T., Marqu\u00e9s, F., & Malik, J. (2017). Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39(1), 128\u2013140.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1323_CR63","doi-asserted-by":"crossref","unstructured":"Qi, L., Jiang, L., Liu, S., Shen, X., & Jia, J. (2019). Amodal instance segmentation with KINS dataset. In Conference on computer vision and pattern recognition (CVPR) (pp. 3014\u20133023). Computer Vision Foundation\/IEEE.","DOI":"10.1109\/CVPR.2019.00313"},{"key":"1323_CR64","doi-asserted-by":"crossref","unstructured":"Ren, M., & Zemel, R. S. (2017). End-to-end instance segmentation with recurrent attention. In Conference on computer vision and pattern recognition (CVPR) (pp. 293\u2013301). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.39"},{"key":"1323_CR65","doi-asserted-by":"crossref","unstructured":"Ren, X., Fowlkes, C. C., Malik, J. (2006). Figure\/ground assignment in natural images. In European conference on computer vision (ECCV) part II (Vol. 3952, pp. 614\u2013627). Lecture notes in computer science, Springer.","DOI":"10.1007\/11744047_47"},{"key":"1323_CR66","doi-asserted-by":"crossref","unstructured":"Romera-Paredes, B., & Torr, P. H. S. (2016). Recurrent instance segmentation. In European conference on computer vision (ECCV) part VI (Vol. 9910, pp. 312\u2013329). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-319-46466-4_19"},{"key":"1323_CR67","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Lecture notes in computer science (pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1323_CR68","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., V\u00e1zquez, D., & L\u00f3pez, A. M. (2016). The SYNTHIA dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Conference on computer vision and pattern recognition (CVPR) (pp. 3234\u20133243). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.352"},{"issue":"3","key":"1323_CR69","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision (IJCV), 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1323_CR70","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A. P., Bishop, R., Rueckert, D., & Wang, Z. (2016). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Conference on computer vision and pattern recognition (CVPR) (pp. 1874\u20131883). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.207"},{"key":"1323_CR71","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International conference on learning representations (ICLR), IEEE Computer Society."},{"key":"1323_CR72","doi-asserted-by":"crossref","unstructured":"Stein, A., & Hebert, M. (2006). Local detection of occlusion boundaries in video. In British machine vision conference (BMVC).","DOI":"10.5244\/C.20.42"},{"key":"1323_CR73","doi-asserted-by":"crossref","unstructured":"Sun, D., Liu, C., & Pfister, H. (2014). Local layering for joint motion estimation and occlusion detection. In Conference on computer vision and pattern recognition (CVPR) (pp. 1098\u20131105). IEEE Computer Society.","DOI":"10.1109\/CVPR.2014.144"},{"key":"1323_CR74","doi-asserted-by":"crossref","unstructured":"Tang, Z., Peng, X., Geng, S., Wu, L., Zhang, S., & Metaxas, D. N. (2018). Quantized densely connected U-Nets for efficient landmark localization. In European conference on computer vision (ECCV) part III (Vol. 11207, pp. 348\u2013364). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01219-9_21"},{"key":"1323_CR75","doi-asserted-by":"crossref","unstructured":"Wang, G., Wang, X., Li, F. W. B., & Liang, X. (2018a). DOOBNet: Deep object occlusion boundary detection from an image. In Asian conference on computer vision (ACCV) part VI (Vol. 11366, pp. 686\u2013702). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-20876-9_43"},{"key":"1323_CR76","doi-asserted-by":"crossref","unstructured":"Wang, P., & Yuille, A. L. (2016). DOC: Deep occlusion estimation from a single image. In European conference on computer vision (ECCV) part I (Vol. 9905, pp. 545\u2013561). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-319-46448-0_33"},{"key":"1323_CR77","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., & Cottrell, G. W. (2018b). Understanding convolution for semantic segmentation. In Winter conference on applications of computer vision (WACV) (pp. 1451\u20131460).","DOI":"10.1109\/WACV.2018.00163"},{"key":"1323_CR78","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhao, X., & Huang, K. (2017). Deep crisp boundaries. In Conference on computer vision and pattern recognition (CVPR) (pp. 1724\u20131732). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.187"},{"key":"1323_CR79","unstructured":"Williams, O., Isard, M., & MacCormick., J. (2011). Estimating disparity and occlusions in stereo video sequences. In Conference on computer vision and pattern recognition (CVPR) (pp. 250\u2013257). IEEE Computer Society."},{"key":"1323_CR80","doi-asserted-by":"crossref","unstructured":"Xie, S., & Tu, Z. (2015). Holistically-nested edge detection. In International conference on computer vision (ICCV) (pp. 1395\u20131403). IEEE Computer Society.","DOI":"10.1109\/ICCV.2015.164"},{"key":"1323_CR81","doi-asserted-by":"crossref","unstructured":"Yang, J., Price, B. L., Cohen, S., Lee, H., & Yang, M. H. (2016). Object contour detection with a fully convolutional encoder\u2013decoder network. In Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.28"},{"key":"1323_CR82","unstructured":"Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? In Advances in neural information processing systems (NIPS) (pp. 3320\u20133328)."},{"key":"1323_CR83","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In International conference on learning representations (ICLR)."},{"key":"1323_CR84","unstructured":"Yu, J., Yang, L., Xu, N., Yang, J., & Huang, T. (2019). Slimmable neural networks. In International conference on learning representations (ICLR)."},{"key":"1323_CR85","doi-asserted-by":"crossref","unstructured":"Yu, Z., Liu, W., Zou, Y., Feng, C., Ramalingam, S., Kumar, B. V. K. V., & Kautz, J. (2018). Simultaneous edge alignment and learning. In European conference on computer vision (ECCV) part III (Vol. 11207, pp. 400\u2013417). Lecture notes in computer science, Springer.","DOI":"10.1007\/978-3-030-01219-9_24"},{"key":"1323_CR86","unstructured":"Zhang, L., Li, X., Arnab, A., Yang, K., Tong, Y., & Torr, P. H. (2019). Dual graph convolutional network for semantic segmentation. In British machine vision conference (BMVC)."},{"key":"1323_CR87","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Tian, Y., Metaxas, D. N., Doll\u00e1r, P. (2017). Semantic amodal segmentation. In Conference on computer vision and pattern recognition (CVPR) (pp. 3001\u20133009). IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.320"},{"issue":"7","key":"1323_CR88","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1109\/34.865184","volume":"22","author":"CL Zitnick","year":"2000","unstructured":"Zitnick, C. L., & Kanade, T. (2000). A cooperative algorithm for stereo matching and occlusion detection. IEEE Transactions on Pattern Analysis Machine Intelligence (TPAMI), 22(7), 675\u2013684.","journal-title":"IEEE Transactions on Pattern Analysis Machine Intelligence (TPAMI)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01323-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-020-01323-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01323-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,27]],"date-time":"2021-03-27T00:37:33Z","timestamp":1616805453000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-020-01323-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,27]]},"references-count":88,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["1323"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01323-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,27]]},"assertion":[{"value":"18 July 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}