{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T13:20:36Z","timestamp":1725888036268},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319591254"},{"type":"electronic","value":"9783319591261"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-59126-1_9","type":"book-chapter","created":{"date-parts":[[2017,5,17]],"date-time":"2017-05-17T20:55:49Z","timestamp":1495054549000},"page":"98-109","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Multimodal Neural Networks: RGB-D for Semantic Segmentation and Object Detection"],"prefix":"10.1007","author":[{"given":"Lukas","family":"Schneider","sequence":"first","affiliation":[]},{"given":"Manuel","family":"Jasch","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn","family":"Fr\u00f6hlich","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Weber","sequence":"additional","affiliation":[]},{"given":"Uwe","family":"Franke","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"R\u00e4tsch","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,5,19]]},"reference":[{"key":"9_CR1","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. In: CVPR (2015)"},{"key":"9_CR2","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2014)"},{"key":"9_CR3","unstructured":"Chen, L.C., Yuille, A.L., Urtasun, R.: Learning deep structured models. In: ICML (2015)"},{"key":"9_CR4","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":"9_CR5","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: Benchmark of Cityscapes dataset. www.cityscapes-dataset.com\/benchmarks\/, Accessed 27 Aug 2016"},{"key":"9_CR6","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"9_CR7","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. In: ICLR (2013)"},{"issue":"8","key":"9_CR8","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Couprie","year":"2013","unstructured":"Couprie, C., Najman, L., Lecun, Y.: Learning Hierarchical features for scene labeling. Trans. PAMI 35(8), 1915\u20131929 (2013)","journal-title":"Trans. PAMI"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Deng, Z., Todorovic, S., Jan Latecki, L.: Semantic segmentation of RGBD images with mutex constraints. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.202"},{"key":"9_CR10","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: IROS (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"issue":"1","key":"9_CR11","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.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 111(1), 98\u2013136 (2015)","journal-title":"IJCV"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"9_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). doi:10.1007\/978-3-319-10584-0_23"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.309"},{"key":"9_CR17","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: Fusenet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: ACCV (2016)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jianping Shi, X.Q., Wang, X., Jia, J.: Pyramid scene parsing network. ArXiv (2016)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"2","key":"9_CR20","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschm\u00fcller","year":"2008","unstructured":"Hirschm\u00fcller, H.: Stereo processing by semiglobal matching and mutual information. Trans. PAMI 30(2), 328\u2013341 (2008)","journal-title":"Trans. PAMI"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Hou, S., Wang, Z., Wu, F.: Deeply exploit depth information for object detection. In: CVPRW (2016)","DOI":"10.1109\/CVPRW.2016.140"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed\/accuracy trade-offs for modern convolutional object detectors. ArXiv (2016)","DOI":"10.1109\/CVPR.2017.351"},{"key":"9_CR23","unstructured":"Jifeng Dai, Y.L., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)"},{"issue":"1","key":"9_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0843-8","volume":"117","author":"SH Khan","year":"2016","unstructured":"Khan, S.H., Bennamoun, M., Sohel, F., Togneri, R., Naseem, I.: Integrating geometrical context for semantic labeling of indoor scenes using RGBD images. IJCV 117(1), 1\u201320 (2016)","journal-title":"IJCV"},{"key":"9_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-319-45886-1_6","volume-title":"Pattern Recognition","author":"I Kre\u0161o","year":"2016","unstructured":"Kre\u0161o, I., \u010cau\u0161evi\u0107, D., Krapac, J., \u0160egvi\u0107, S.: Convolutional scale invariance for semantic segmentation. In: Rosenhahn, B., Andres, B. (eds.) GCPR 2016. LNCS, vol. 9796, pp. 64\u201375. Springer, Cham (2016). doi:10.1007\/978-3-319-45886-1_6"},{"key":"9_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-319-46475-6_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Li","year":"2016","unstructured":"Li, Z., Gan, Y., Liang, X., Yu, Y., Cheng, H., Lin, L.: LSTM-CF: unifying context modeling and fusion with LSTMs for RGB-D scene labeling. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 541\u2013557. Springer, Cham (2016). doi:10.1007\/978-3-319-46475-6_34"},{"key":"9_CR27","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: ICLR (2013)"},{"key":"9_CR28","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, Cham (2014). doi:10.1007\/978-3-319-10602-1_48"},{"key":"9_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). doi:10.1007\/978-3-319-46448-0_2"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"9_CR31","unstructured":"M. Jasch, T. Weber, M.R.: Fast and robust RGB-D scene labeling for autonomous driving. In: ICSCC, JCP (2016, to appear)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"3","key":"9_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"15","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. IJCV 15(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"9_CR34","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)"},{"key":"9_CR35","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Ecology (2015)"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.A.: Semantic scene completion from a single depth image. In: CVPR (2017, to appear)","DOI":"10.1109\/CVPR.2017.28"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P.: Going deeper with convolutions. In: CVPR (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"9_CR39","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2015)"},{"key":"9_CR40","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59126-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:31:35Z","timestamp":1710232295000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-59126-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319591254","9783319591261"],"references-count":40,"URL":"http:\/\/dx.doi.org\/10.1007\/978-3-319-59126-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"19 May 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Troms\u00f8","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/scia2017.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}