{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:44:27Z","timestamp":1781541867415,"version":"3.54.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01252-6_9","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T13:48:05Z","timestamp":1538747285000},"page":"144-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":227,"title":["Depth-Aware CNN for RGB-D Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8114-8271","authenticated-orcid":false,"given":"Weiyue","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrich","family":"Neumann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"9_CR1","unstructured":"Armeni, I., Sax, A., Zamir, A.R., Savarese, S.: Joint 2D\u20133D-semantic data for indoor scene understanding. ArXiv e-prints (2017)"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/978-3-319-46487-9_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JT Barron","year":"2016","unstructured":"Barron, J.T., Poole, B.: The fast bilateral solver. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 617\u2013632. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_38"},{"key":"9_CR3","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/1276377.1276506","volume":"26","author":"J Chen","year":"2007","unstructured":"Chen, J., Paris, S., Durand, F.: Real-time edge-aware image processing with the bilateral grid. ACM Trans. Graph. (TOG) 26, 103 (2007)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"9_CR4","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 (2015)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Cai, R., Li, Z., Zhao, X., Huang, K.: Locality-sensitive deconvolution networks with gated fusion for RGB-D indoor semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.161"},{"key":"9_CR6","unstructured":"Couprie, C., Farabet, C., Najman, L., Lecun, Y.: Indoor semantic segmentation using depth information. In: ICLR (2013)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"9_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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"9_CR9","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). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"9_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-54181-5_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"C Hazirbas","year":"2017","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213\u2013228. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Chiu, W.C., Keuper, M., Fritz, M.: STD2P: RGBD semantic segmentation using spatio-temporal data-driven pooling. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.757"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation on point clouds. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00278"},{"key":"9_CR14","unstructured":"Huang, Q., Wang, W., Zhou, K., You, S., Neumann, U.: Scene labeling using gated recurrent units with explicit long range conditioning. arXiv preprint arXiv:1611.07485 (2016)"},{"key":"9_CR15","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., kavukcuoglu, k.: Spatial transformer networks. In: NIPS (2015)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Janoch, A., et al.: A category-level 3-d object dataset: Putting the kinect to work. In: ICCV workshop (2011)","DOI":"10.1109\/ICCVW.2011.6130382"},{"key":"9_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-319-10590-1_44","volume-title":"Computer Vision \u2013 ECCV 2014","author":"SH Khan","year":"2014","unstructured":"Khan, S.H., Bennamoun, M., Sohel, F., Togneri, R.: Geometry driven semantic labeling of indoor scenes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 679\u2013694. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_44"},{"key":"9_CR18","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). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_34"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Lin, D., Chen, G., Cohen-Or, D., Heng, P.A., Huang, H.: Cascaded feature network for semantic segmentation of RGB-D images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.147"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Ma, L., Stueckler, J., Kerl, C., Cremers, D.: Multi-view deep learning for consistent semantic mapping with RGB-D cameras. In: IROS (2017)","DOI":"10.1109\/IROS.2017.8202213"},{"key":"9_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"9_CR23","unstructured":"Park, S.J., Hong, K.S., Lee, S.: RDFNet: RGB-D multi-level residual feature fusion for indoor semantic segmentation. In: ICCV (2017)"},{"key":"9_CR24","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: CVPR (2017)"},{"key":"9_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS (2017)"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3d graph neural networks for RGBD semantic segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.556"},{"key":"9_CR27","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: CVPR (2012)"},{"key":"9_CR28","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. In: PAMI (2016)"},{"key":"9_CR29","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_CR30","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.94"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.28"},{"key":"9_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-319-46454-1_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wang","year":"2016","unstructured":"Wang, J., Wang, Z., Tao, D., See, S., Wang, G.: Learning common and specific features for RGB-D semantic segmentation with deconvolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 664\u2013679. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_40"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Wang, W., Huang, Q., You, S., Yang, C., Neumann, U.: Shape inpainting using 3d generative adversarial network and recurrent convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.252"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., Wang, N., Wu, X., You, S., Yang, C., Neumann, U.: Self-paced cross-modality transfer learning for efficient road segmentation. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989166"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, R., Huang, Q., Neumann, U.: SGPN: similarity group proposal network for 3d point cloud instance segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00272"},{"key":"9_CR36","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01252-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T01:02:38Z","timestamp":1664931758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","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"}]}}