{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:42:27Z","timestamp":1779295347257,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319541808","type":"print"},{"value":"9783319541815","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-54181-5_12","type":"book-chapter","created":{"date-parts":[[2017,3,9]],"date-time":"2017-03-09T15:27:37Z","timestamp":1489073257000},"page":"180-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":163,"title":["Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks"],"prefix":"10.1007","author":[{"given":"Nicolas","family":"Audebert","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertrand","family":"Le Saux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9bastien","family":"Lef\u00e8vre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,10]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2014","unstructured":"Everingham, M., Eslami, S.M.A., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Heidelberg (2014). doi:10.1007\/978-3-319-10602-1_48"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Lagrange, A., Le Saux, B., Beaupere, A., Boulch, A., Chan-Hon-Tong, A., Herbin, S., Randrianarivo, H., Ferecatu, M.: Benchmarking classification of earth-observation data: from learning explicit features to convolutional networks. In: IEEE International Geosciences and Remote Sensing Symposium (IGARSS), pp. 4173\u20134176 (2015)","DOI":"10.1109\/IGARSS.2015.7326745"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Paisitkriangkrai, S., Sherrah, J., Janney, P., Van Den Hengel, A.: Effective semantic pixel labelling with convolutional networks and conditional random fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 36\u201343 (2015)","DOI":"10.1109\/CVPRW.2015.7301381"},{"key":"12_CR6","first-page":"3","volume":"1","author":"F Rottensteiner","year":"2012","unstructured":"Rottensteiner, F., Sohn, G., Jung, J., Gerke, M., Baillard, C., Benitez, S., Breitkopf, U.: The ISPRS benchmark on urban object classification and 3d building reconstruction. ISPRS Ann. Photogrammetry Remote Sens. Spat. Inf. Sci. 1, 3 (2012)","journal-title":"ISPRS Ann. Photogrammetry Remote Sens. Spat. Inf. Sci."},{"key":"12_CR7","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"12_CR8","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.S.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Arnab, A., Jayasumana, S., Zheng, S., Torr, P.: Higher order conditional random fields in deep neural networks (2015). arXiv:1511.08119 [cs]","DOI":"10.1007\/978-3-319-46475-6_33"},{"key":"12_CR11","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR12","unstructured":"Wu, Z., Shen, C., Van Den Hengel, A.: High-performance semantic segmentation using very deep fully convolutional networks (2016). arXiv:1604.04339 [cs]"},{"key":"12_CR13","unstructured":"Yan, Z., Zhang, H., Jia, Y., Breuel, T., Yu, Y.: Combining the best of convolutional layers and recurrent layers: a hybrid network for semantic segmentation. arXiv:1603.04871 [cs] (2016)"},{"key":"12_CR14","unstructured":"Zhao, J., Mathieu, M., Goroshin, R., LeCun, Y.: Stacked what-where auto-encoders. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"12_CR16","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)"},{"key":"12_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-642-15567-3_16","volume-title":"Computer Vision \u2013 ECCV 2010","author":"V Mnih","year":"2010","unstructured":"Mnih, V., Hinton, G.E.: Learning to detect roads in high-resolution aerial images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 210\u2013223. Springer, Heidelberg (2010). doi:10.1007\/978-3-642-15567-3_16"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Penatti, O., Nogueira, K., Dos Santos, J.: Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 44\u201351 (2015)","DOI":"10.1109\/CVPRW.2015.7301382"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Campos-Taberner, M., Romero-Soriano, A., Gatta, C., Camps-Valls, G., Lagrange, A., Le Saux, B., Beaup\u00e8re, A., Boulch, A., Chan-Hon-Tong, A., Herbin, S., Randrianarivo, H., Ferecatu, M., Shimoni, M., Moser, G., Tuia, D.: Processing of extremely high-resolution LiDAR and RGB data: outcome of the 2015 IEEE GRSS data fusion contest part A: 2-D contest. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. PP, 1\u201313 (2016)","DOI":"10.1109\/JSTARS.2016.2569162"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Nogueira, K., Penatti, O.A.B., Dos Santos, J.A.: Towards better exploiting convolutional neural networks for remote sensing scene classification. arXiv:1602.01517 [cs] (2016)","DOI":"10.1016\/j.patcog.2016.07.001"},{"key":"12_CR21","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.isprsjprs.2016.01.004","volume":"113","author":"W Zhao","year":"2016","unstructured":"Zhao, W., Du, S.: Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS J. Photogrammetry Remote Sens. 113, 155\u2013165 (2016)","journal-title":"ISPRS J. Photogrammetry Remote Sens."},{"key":"12_CR22","doi-asserted-by":"publisher","first-page":"473","DOI":"10.5194\/isprsannals-III-3-473-2016","volume":"3","author":"D Marmanis","year":"2016","unstructured":"Marmanis, D., Wegner, J.D., Galliani, S., Schindler, K., Datcu, M., Stilla, U.: Semantic segmentation of aerial images with an ensemble of CNNs. ISPRS Ann. Photogrammetry Remote Sens. Spat. Inf. Sci. 3, 473\u2013480 (2016)","journal-title":"ISPRS Ann. Photogrammetry Remote Sens. Spat. Inf. Sci."},{"key":"12_CR23","unstructured":"Gerke, M.: Use of the stair vision library within the ISPRS 2d semantic labeling benchmark (Vaihingen). Technical report, International Institute for Geo-Information Science and Earth Observation (2015)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of the British Machine Vision Conference, pp. 6.1\u20136.12. British Machine Vision Association (2014)","DOI":"10.5244\/C.28.6"},{"key":"12_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs] (2014)"},{"key":"12_CR26","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"12_CR28","unstructured":"Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"12_CR29","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","volume":"13","author":"D Marmanis","year":"2016","unstructured":"Marmanis, D., Datcu, M., Esch, T., Stilla, U.: Deep learning earth observation classification using imagenet pretrained networks. IEEE Geosci. Remote Sens. Lett. 13, 105\u2013109 (2016)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Liao, R., Tao, X., Li, R., Ma, Z., Jia, J.: Video super-resolution via deep draft-ensemble learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 531\u2013539 (2015)","DOI":"10.1109\/ICCV.2015.68"},{"key":"12_CR32","unstructured":"Liao, Z., Carneiro, G.: Competitive multi-scale convolution. arXiv:1511.05635 [cs] (2015)"},{"key":"12_CR33","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th international conference on machine learning (ICML 2011), pp. 689\u2013696 (2011)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgard, W.: Multimodal deep learning for robust RGB-D object recognition. In: Proceedings of the International Conference on Intelligent Robots and Systems, pp. 681\u2013687. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Quang, N.T., Thuy, N.T., Sang, D.V., Binh, H.T.T.: An efficient framework for pixel-wise building segmentation from aerial images. In: Proceedings of the Sixth International Symposium on Information and Communication Technology, p. 43. ACM (2015)","DOI":"10.1145\/2833258.2833272"},{"key":"12_CR36","unstructured":"Boulch, A.: DAG of convolutional networks for semantic labeling. Technical report, Office national d\u2019\u00e9tudes et de recherchesa\u00e9rospatiales (2015)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Van Den Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2016.348"},{"key":"12_CR38","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320\u20133328 (2014)"},{"key":"12_CR39","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1127\/1432-8364\/2010\/0041","volume":"2","author":"M Cramer","year":"2010","unstructured":"Cramer, M.: The DGPF test on digital aerial camera evaluation - overview and test design. Photogrammetrie - Fernerkundung - Geoinformation 2, 73\u201382 (2010)","journal-title":"Photogrammetrie - Fernerkundung - Geoinformation"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54181-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T15:26:57Z","timestamp":1710170817000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-54181-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319541808","9783319541815"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54181-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"10 March 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.accv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}