{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:37:29Z","timestamp":1774600649822,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464749","type":"print"},{"value":"9783319464756","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\/978-3-319-46475-6_34","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T08:48:10Z","timestamp":1474015690000},"page":"541-557","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":106,"title":["LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Wu, C., Lenz, I., Saxena, A.: Hierarchical semantic labeling for task-relevant RGB-D perception. In: Robotics: Science and Systems (RSS) (2014)","DOI":"10.15607\/RSS.2014.X.006"},{"key":"34_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013)"},{"key":"34_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-642-32060-6_26","volume-title":"RoboCup 2011: Robot Soccer World Cup XV","author":"D Holz","year":"2012","unstructured":"Holz, D., Holzer, S., Rusu, R.B., Behnke, S.: Real-time plane segmentation using RGB-D cameras. In: R\u00f6fer, T., Mayer, N.M., Savage, J., Saranl\u0131, U. (eds.) RoboCup 2011. LNCS, vol. 7416, pp. 306\u2013317. Springer, Heidelberg (2012)"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Schuster, S., Krishna, R., Chang, A., Fei-Fei, L., Manning, C.D.: Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In: Proceedings of the Fourth Workshop on Vision and Language, pp. 70\u201380 (2015)","DOI":"10.18653\/v1\/W15-2812"},{"issue":"2","key":"34_CR5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/2790296","volume":"35","author":"Z Yan","year":"2016","unstructured":"Yan, Z., Zhang, H., Wang, B., Paris, S., Yu, Y.: Automatic photo adjustment using deep neural networks. ACM Trans. Graph. 35(2), 11 (2016)","journal-title":"ACM Trans. Graph."},{"issue":"8","key":"34_CR6","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":"34_CR7","doi-asserted-by":"crossref","unstructured":"Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1\u20138. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"34_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/978-3-642-15555-0_26","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Tighe","year":"2010","unstructured":"Tighe, J., Lazebnik, S.: SuperParsing: scalable nonparametric image parsing with superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 352\u2013365. Springer, Heidelberg (2010)"},{"key":"34_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0843-8","volume":"117","author":"SH Khan","year":"2015","unstructured":"Khan, S.H., Bennamoun, M., Sohel, F., Togneri, R., Naseem, I.: Integrating geometrical context for semantic labeling of indoor scenes using RGBD images. Int. J. Comput. Vis. 117, 1\u201320 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"34_CR10","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":"34_CR11","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.: 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":"34_CR12","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:1412.7062 (2014)"},{"key":"34_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":"34_CR14","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. arXiv preprint arXiv:1511.02300 (2015)","DOI":"10.1109\/CVPR.2016.94"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1377\u20131385 (2015)","DOI":"10.1109\/ICCV.2015.162"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Liang, X., Shen, X., Xiang, D., Feng, J., Lin, L., Yan, S.: Semantic object parsing with local-global long short-term memory. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.347"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Byeon, W., Breuel, T.M., Raue, F., Liwicki, M.: Scene labeling with LSTM recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3547\u20133555 (2015)","DOI":"10.1109\/CVPR.2015.7298977"},{"key":"34_CR18","unstructured":"Pinheiro, P., Collobert, R.: Recurrent convolutional neural networks for scene labeling. In: Proceedings of the 31st International Conference on Machine Learning (ICML 2014), pp. 82\u201390 (2014)"},{"key":"34_CR19","unstructured":"Visin, F., Kastner, K., Cho, K., Matteucci, M., Courville, A., Bengio, Y.: Renet: a recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:1505.00393 (2015)"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, M.P., Koller, D.: Efficiently selecting regions for scene understanding. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3217\u20133224. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540072"},{"key":"34_CR22","unstructured":"Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)"},{"key":"34_CR23","unstructured":"Lempitsky, V., Vedaldi, A., Zisserman, A.: Pylon model for semantic segmentation. In: Advances in Neural Information Processing Systems, pp. 1485\u20131493 (2011)"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2759\u20132766. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247999"},{"issue":"2","key":"34_CR25","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-014-0777-6","volume":"112","author":"S Gupta","year":"2015","unstructured":"Gupta, S., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Indoor scene understanding with RGB-D images: bottom-up segmentation, object detection and semantic segmentation. Int. J. Comput. Vis. 112(2), 133\u2013149 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"34_CR26","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. 24(11), 4459\u20134473 (2015)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"34_CR27","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/LRA.2016.2532927","volume":"2","author":"F Husain","year":"2017","unstructured":"Husain, F., Schulz, H., Dellen, B., Torras, C., Behnke, S.: Combining semantic and geometric features for object class segmentation of indoor scenes. IEEE Rob. Autom. Lett. 2(1), 49\u201355 (2017)","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"4","key":"34_CR28","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1080\/09540098908915650","volume":"1","author":"J Schmidhuber","year":"1989","unstructured":"Schmidhuber, J.: A local learning algorithm for dynamic feedforward and recurrent networks. Connection Sci. 1(4), 403\u2013412 (1989)","journal-title":"Connection Sci."},{"issue":"2","key":"34_CR29","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"8","key":"34_CR30","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"34_CR31","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 545\u2013552 (2009)"},{"key":"34_CR32","unstructured":"Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. In: Advances in Neural Information Processing Systems, pp. 2980\u20132988 (2015)"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Li, G., Yu, Y.: Deep contrast learning for salient object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.58"},{"key":"34_CR34","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":"34_CR35","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-1-4471-4640-7_8","volume-title":"Consumer Depth Cameras for Computer Vision","author":"A Janoch","year":"2013","unstructured":"Janoch, A., Karayev, S., Jia, Y., Barron, J.T., Fritz, M., Saenko, K., Darrell, T.: A category-level 3D object dataset: putting the kinect to work. In: Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.) Consumer Depth Cameras for Computer Vision, pp. 141\u2013165. Springer, Heidelberg (2013)"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, J., Owens, A., Torralba, A.: SUN3D: a database of big spaces reconstructed using SfM and object labels. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1625\u20131632 (2013)","DOI":"10.1109\/ICCV.2013.458"},{"key":"34_CR37","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"},{"issue":"5","key":"34_CR38","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978\u2013994 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR39","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Toward real-time indoor semantic segmentation using depth information. J. Mach. Learn. Res. (2014)"},{"issue":"2","key":"34_CR40","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167\u2013181 (2004)","journal-title":"Int. J. Comput. Vis."}],"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\/978-3-319-46475-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:14:58Z","timestamp":1749582898000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46475-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464749","9783319464756"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46475-6_34","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":"17 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"}]}}