{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:48:44Z","timestamp":1767340124662},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319458854"},{"type":"electronic","value":"9783319458861"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45886-1_6","type":"book-chapter","created":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T08:41:50Z","timestamp":1472200910000},"page":"64-75","source":"Crossref","is-referenced-by-count":30,"title":["Convolutional Scale Invariance for Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Ivan","family":"Kre\u0161o","sequence":"first","affiliation":[]},{"given":"Denis","family":"\u010cau\u0161evi\u0107","sequence":"additional","affiliation":[]},{"given":"Josip","family":"Krapac","sequence":"additional","affiliation":[]},{"given":"Sini\u0161a","family":"\u0160egvi\u0107","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,27]]},"reference":[{"key":"6_CR1","unstructured":"Arnab, A., Jayasumana, S., Zheng, S., Torr, P.H.S.: Higher order potentials in end-to-end trainable conditional random fields. CoRR abs\/1511.08119 (2015)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Banica, D., Sminchisescu, C.: Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, pp. 3517\u20133526, 7\u201312 June 2015","DOI":"10.1109\/CVPR.2015.7298974"},{"key":"6_CR3","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, ICLR 2015, San Diego, California (2014)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Las Vegas, Nevada (2016) (to appear)","DOI":"10.1109\/CVPR.2016.396"},{"key":"6_CR5","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A., Ma, H., Fidler, S., Urtasun, R.: 3d object proposals for accurate object class detection. In: NIPS (2015)"},{"key":"6_CR6","unstructured":"Cordts, M., Omran, M., Ramos, S., Scharw\u00e4chter, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset. In: CVPR Workshop on the Future of Datasets in Vision (2015)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Divvala, S.K., Hoiem, D., Hays, J., Efros, A.A., Hebert, M.: An empirical study of context in object detection. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami, Florida, USA, pp. 1271\u20131278, 20\u201325 June 2009","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, pp. 2650\u20132658, 7\u201313 December 2015","DOI":"10.1109\/ICCV.2015.304"},{"issue":"1","key":"6_CR9","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"6_CR10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput, Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput, Vis."},{"issue":"8","key":"6_CR11","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915\u20131929 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. (IJRR) (2013)","DOI":"10.1177\/0278364913491297"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hirschm\u00fcller, H.: Stereo vision in structured environments by consistent semi-global matching. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), New York, NY, USA, pp. 2386\u20132393, 17\u201322 June 2006","DOI":"10.1109\/CVPR.2006.294"},{"key":"6_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning, ICML 2015, Lille, France, pp. 448\u2013456, 6\u201311 July 2015"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, MM 2014, Orlando, FL, USA, 03\u201307 November 2014, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"6_CR16","unstructured":"Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. CoRR abs\/1511.02680 (2015)"},{"key":"6_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"6_CR18","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. In: Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, Proceedings of a meeting held 12\u201314, Granada, Spain, pp. 109\u2013117, December 2011"},{"key":"6_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Annual Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, United States, pp. 1106\u20131114 (2012)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Shi, J., Pollefeys, M.: Pulling things out of perspective. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23\u201328 June 2014, pp. 89\u201396 (2014)","DOI":"10.1109\/CVPR.2014.19"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., van dan Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Las Vegas, Nevada (2016) (to appear)","DOI":"10.1109\/CVPR.2016.348"},{"key":"6_CR22","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, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Martinovic, A., Knopp, J., Riemenschneider, H., Gool, L.V.: 3d all the way: semantic segmentation of urban scenes from start to end in 3d. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015","DOI":"10.1109\/CVPR.2015.7299075"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mostajabi, M., Yadollahpour, P., Shakhnarovich, G.: Feedforward semantic segmentation with zoom-out features. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015, pp. 3376\u20133385 (2015)","DOI":"10.1109\/CVPR.2015.7298959"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Ros, G., Ramos, S., Granados, M., Bakhtiary, A., V\u00e1zquez, D., L\u00f3pez, A.M.: Vision-based offline-online perception paradigm for autonomous driving. In: 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2014, Waikoloa, HI, USA, 5\u20139 January 2015, pp. 231\u2013238 (2015)","DOI":"10.1109\/WACV.2015.38"},{"key":"6_CR27","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations, ICLR 2014, Banff, Canada, pp. 1\u201316 (2014)"},{"issue":"1","key":"6_CR28","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J Shotton","year":"2009","unstructured":"Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vis. 81(1), 2\u201323 (2009)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, ICLR 2015, San Diego, California, pp. 1\u201316 (2014)"},{"issue":"2","key":"6_CR30","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"PA Viola","year":"2004","unstructured":"Viola, P.A., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR31","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, pp. 1\u20139 (2016)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Zbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. CoRR abs\/1510.05970 (2015)","DOI":"10.1109\/CVPR.2015.7298767"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45886-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,12]],"date-time":"2019-09-12T20:16:33Z","timestamp":1568319393000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45886-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319458854","9783319458861"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45886-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}