{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:40:30Z","timestamp":1778082030097,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464534","type":"print"},{"value":"9783319464541","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46454-1_40","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:15:09Z","timestamp":1473930909000},"page":"664-679","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":115,"title":["Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks"],"prefix":"10.1007","author":[{"given":"Jinghua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"key":"40_CR1","unstructured":"Socher, R., Lin, C.C., Ng, A.Y., Manning, C.D.: Parsing natural scenes and natural language with recursive neural networks. In: ICML (2011)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Shuai, B., Zuo, Z., Wang, G., Wang, B.: Dag-recurrent neural networks for scene labeling. Comput. Sci. (2015)","DOI":"10.1109\/CVPR.2016.394"},{"issue":"8","key":"40_CR3","doi-asserted-by":"publisher","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":"40_CR4","unstructured":"Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. In: NIPS 2015 (2015)"},{"issue":"5","key":"40_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2016.2533862","volume":"25","author":"B Shuai","year":"2016","unstructured":"Shuai, B., Zuo, Z., Wang, G., Wang, B.: Scene parsing with integration of parametric and non-parametric models. IEEE Trans. Image Process. 25(5), 1\u20131 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. arXiv preprint arXiv:1505.04366 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"40_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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, Part V. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012)"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Silberman, N., Fergus, R.: Indoor scene segmentation using a structured light sensor. In: ICCV Workshops, pp. 601\u2013608 (2011)","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: CVPR, pp. 2759\u20132766 (2012)","DOI":"10.1109\/CVPR.2012.6247999"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: CVPR, pp. 564\u2013571 (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"40_CR11","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. In: International Conference on Learning Representations. Number arXiv preprint arXiv:1301.3572 (2013)"},{"key":"40_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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, Part I. LNCS, vol. 8689, pp. 679\u2013694. Springer, Heidelberg (2014)"},{"key":"40_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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, Part VII. LNCS, vol. 8695, pp. 345\u2013360. Springer, Heidelberg (2014)"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Deng, Z., Todorovic, S., Latecki, L.J.: Semantic segmentation of RGBD images with mutex constraints. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.202"},{"key":"40_CR15","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: Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298974"},{"issue":"11","key":"40_CR16","doi-asserted-by":"publisher","first-page":"4459","DOI":"10.1109\/TIP.2015.2465133","volume":"24","author":"A Wang","year":"2015","unstructured":"Wang, A., Lu, J., Cai, J., Wang, G., Cham, T.J.: Unsupervised joint feature learning and encoding for RGB-D scene labeling. IEEE Trans. Image Process. A Publication of the IEEE Signal Processing Society 24(11), 4459\u20134473 (2015)","journal-title":"IEEE Trans. Image Process. A Publication of the IEEE Signal Processing Society"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Shuai, B., Wang, G., Zuo, Z., Wang, B., Zhao, L.: Integrating parametric and non-parametric models for scene labeling. In: IEEE Conference on Computer Vision and Pattern Recognition. (2015)","DOI":"10.1109\/CVPR.2015.7299053"},{"key":"40_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1007\/978-3-319-10602-1_30","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Wang","year":"2014","unstructured":"Wang, A., Lu, J., Wang, G., Cai, J., Cham, T.-J.: Multi-modal unsupervised feature learning for RGB-D scene labeling. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 453\u2013467. Springer, Heidelberg (2014)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Wang, A., Cai, J., Lu, J., Cham, T.J.: MMSS: Multi-modal sharable and specific feature learning for RGB-D object recognition. In: IEEE International Conference on Computer Vision, pp. 1125\u20131133 (2015)","DOI":"10.1109\/ICCV.2015.134"},{"issue":"11","key":"40_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSP.2015.2441781","volume":"22","author":"B Shuai","year":"2015","unstructured":"Shuai, B., Zuo, Z., Wang, G.: Quaddirectional 2d-recurrent neural networks for image labeling. IEEE Sig. Process. Lett. 22(11), 1 (2015)","journal-title":"IEEE Sig. Process. Lett."},{"key":"40_CR21","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: ICML 2011, pp. 689\u2013696 (2011)"},{"key":"40_CR22","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML 2015, pp. 1180\u20131189 (2015)"},{"key":"40_CR23","unstructured":"Sohn, K., Shang, W., Lee, H.: Improved multimodal deep learning with variation of information. In: NIPS, pp. 2141\u20132149 (2014)"},{"key":"40_CR24","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: CML 2015, JMLR Workshop and Conference Proceedings, pp. 97\u2013105 (2015)"},{"key":"40_CR25","unstructured":"Koppula, H.S., Anand, A., Joachims, T., Saxena, A.: Semantic labeling of 3d point clouds for indoor scenes. In: NIPS, pp. 244\u2013252 (2011)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR 2015 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"40_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) NIPS, pp. 1097\u20131105 (2012)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L.C., Murphy, K., Yuille, A.L.: Weakly-and semi-supervised learning of a DCNN for semantic image segmentation. arXiv preprint arXiv:1502.02734 (2015)","DOI":"10.1109\/ICCV.2015.203"},{"key":"40_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9096-9","volume-title":"Reproducing Kernel Hilbert Spaces in Probability and Statistics","author":"A Berlinet","year":"2004","unstructured":"Berlinet, A., Thomas-Agnan, C.: Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer, Dordrecht (2004)"},{"key":"40_CR30","unstructured":"Gretton, A., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K., Sriperumbudur, B.K.: Optimal kernel choice for large-scale two-sample tests. In: NIPS, pp. 1205\u20131213. Curran Associates, Inc. (2012)"},{"key":"40_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 391\u2013405. Springer, Heidelberg (2014)"},{"key":"40_CR32","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":"40_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"40_CR35","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, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Pei, D., Liu, H., Liu, Y., Sun, F.: Unsupervised multimodal feature learning for semantic image segmentation. In: IJCNN, pp. 1\u20136 (2013)","DOI":"10.1109\/IJCNN.2013.6706748"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3D semantic mapping of indoor scenes from RGB-D images. In: ICRA (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"issue":"4","key":"40_CR38","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s11554-013-0379-5","volume":"10","author":"J St\u00fcckler","year":"2015","unstructured":"St\u00fcckler, J., Waldvogel, B., Schulz, H., Behnke, S.: Dense real-time mapping of object-class semantics from RGB-D video. J. Real-Time Image Process. 10(4), 599\u2013609 (2015)","journal-title":"J. Real-Time Image Process."},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Muller, A.C., Behnke, S.: Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images. In: ICRA, pp. 6232\u20136237 (2014)","DOI":"10.1109\/ICRA.2014.6907778"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46454-1_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:01:12Z","timestamp":1749582072000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46454-1_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464534","9783319464541"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46454-1_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"16 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}