{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:09:37Z","timestamp":1761808177016,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319781983"},{"type":"electronic","value":"9783319781990"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-78199-0_37","type":"book-chapter","created":{"date-parts":[[2018,3,21]],"date-time":"2018-03-21T00:13:52Z","timestamp":1521591232000},"page":"564-579","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3137-1405","authenticated-orcid":false,"given":"M\u00e5ns","family":"Larsson","sequence":"first","affiliation":[]},{"given":"Anurag","family":"Arnab","sequence":"additional","affiliation":[]},{"given":"Fredrik","family":"Kahl","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,22]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Adams, A., Baek, J., Davis, M.A.: Fast high-dimensional filtering using the permutohedral lattice. In: Computer Graphics Forum (2010)","DOI":"10.1111\/j.1467-8659.2009.01645.x"},{"key":"37_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-319-46475-6_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Arnab","year":"2016","unstructured":"Arnab, A., Jayasumana, S., Zheng, S., Torr, P.H.S.: Higher order conditional random fields in deep neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 524\u2013540. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_33"},{"key":"37_CR3","unstructured":"Belanger, D., McCallum, A.: Structured prediction energy networks. In: International Conference on Machine Learning (2016)"},{"key":"37_CR4","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/8579.001.0001","volume-title":"Markov Random Fields for Vision and Image Processing","author":"A Blake","year":"2011","unstructured":"Blake, A., Kohli, P., Rother, C.: Markov Random Fields for Vision and Image Processing. MIT Press, Cambridge (2011)"},{"key":"37_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/3-540-47967-8_8","volume-title":"Computer Vision \u2014 ECCV 2002","author":"E Borenstein","year":"2002","unstructured":"Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109\u2013122. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-47967-8_8"},{"key":"37_CR6","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/S0166-218X(01)00341-9","volume":"123","author":"E Boros","year":"2002","unstructured":"Boros, E., Hammer, P.L.: Pseudo-boolean optimization. Discret. Appl. Math. 123, 155\u2013225 (2002)","journal-title":"Discret. Appl. Math."},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Bottou, L., Bengio, Y., Le Cun, Y.: Global training of document processing systems using graph transformer networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 489\u2013494. IEEE (1997)","DOI":"10.1109\/CVPR.1997.609370"},{"issue":"11","key":"37_CR8","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1109\/34.969114","volume":"23","author":"Y Boykov","year":"2001","unstructured":"Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222\u20131239 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-319-46478-7_25","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Chandra","year":"2016","unstructured":"Chandra, S., Kokkinos, I.: Fast, exact and multi-scale inference for semantic image segmentation with deep Gaussian CRFs. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 402\u2013418. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_25"},{"key":"37_CR10","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: International Conference on Learning Representations (2015)"},{"key":"37_CR11","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv preprint arXiv:1606.00915 (2016)"},{"key":"37_CR12","unstructured":"Chen, L.C., Schwing, A.G., Yuille, A.L., Urtasun, R.: Learning deep structured models. In: International Conference Machine Learning, Lille, France (2015)"},{"key":"37_CR13","unstructured":"Chen, Y., Ye, X.: Projection onto a simplex. arXiv preprint arXiv:1101.6081 (2011)"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"37_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-46475-6_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Desmaison","year":"2016","unstructured":"Desmaison, A., Bunel, R., Kohli, P., Torr, P.H.S., Kumar, M.P.: Efficient continuous relaxations for dense CRF. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 818\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_50"},{"key":"37_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-319-46487-9_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Ghiasi","year":"2016","unstructured":"Ghiasi, G., Fowlkes, C.C.: Laplacian pyramid reconstruction and refinement for semantic segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 519\u2013534. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_32"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Jafari, O.H., Groth, O., Kirillov, A., Yang, M.Y., Rother, C.: Analyzing modular CNN architectures for joint depth prediction and semantic segmentation. In: International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989537"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Jampani, V., Kiefel, M., Gehler, P.V.: Learning sparse high dimensional filters: image filtering, dense CRFs and bilateral neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2016","DOI":"10.1109\/CVPR.2016.482"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"37_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-319-54184-6_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"A Kirillov","year":"2017","unstructured":"Kirillov, A., Schlesinger, D., Zheng, S., Savchynskyy, B., Torr, P.H.S., Rother, C.: Joint training of generic CNN-CRF models with stochastic optimization. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 221\u2013236. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_14"},{"key":"37_CR23","volume-title":"Probabilistic Graphical Models","author":"D Koller","year":"2009","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models. MIT Press, Cambridge (2009)"},{"key":"37_CR24","unstructured":"Kraehenbuehl, P., Koltun, V.: Parameter learning and convergent inference for dense random fields. In: Proceedings of the 30th International Conference on Machine Learning, pp. 513\u2013521 (2013)"},{"key":"37_CR25","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Neural Information Processing Systems (2011)"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2016","DOI":"10.1109\/CVPR.2016.348"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.162"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"37_CR29","unstructured":"Peng, J., Bo, L., Xu, J.: Conditional neural fields. In: Advances in Neural Information Processing Systems, pp. 1419\u20131427 (2009)"},{"key":"37_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural Information Processing Systems (2015)"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cGrabCut\u201d: interactive foreground extraction using iterated graph cuts. In: ACM Transactions on Graphics, pp. 309\u2013314 (2004)","DOI":"10.1145\/1186562.1015720"},{"key":"37_CR32","unstructured":"Schwing, A., Urtasun, R.: Fully connected deep structured networks. arXiv preprint arXiv:1503.02351 (2015)"},{"key":"37_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Lenc, K.: MatConvNet - convolutional neural networks for MATLAB. In: Proceeding of the ACM International Conference on Multimedia (2015)","DOI":"10.1145\/2733373.2807412"},{"key":"37_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-33715-4_3","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Vineet","year":"2012","unstructured":"Vineet, V., Warrell, J., Torr, P.H.S.: Filter-based mean-field inference for random fields with higher-order terms and product label-spaces. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 31\u201344. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_3"},{"key":"37_CR36","unstructured":"Wang, P., Shen, X., Lin, Z., Cohen, S., Price, B., Yuille, A.: Towards unified depth and semantic prediction from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)"},{"key":"37_CR37","unstructured":"Wang, W., Fidler, S., Urtasun, R.: Proximal deep structured models. In: Neural Information Processing Systems (2016)"},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.: Conditional random fields as recurrent neural networks. In: International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Lecture Notes in Computer Science","Energy Minimization Methods in Computer Vision and Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78199-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,13]],"date-time":"2019-10-13T01:54:35Z","timestamp":1570931675000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78199-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319781983","9783319781990"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78199-0_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}