{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:16:11Z","timestamp":1778080571648,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319494081","type":"print"},{"value":"9783319494098","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\/978-3-319-49409-8_66","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T23:14:24Z","timestamp":1602285264000},"page":"804-820","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Can Ground Truth Label Propagation from Video Help Semantic Segmentation?"],"prefix":"10.1007","author":[{"given":"Siva Karthik","family":"Mustikovela","sequence":"first","affiliation":[]},{"given":"Michael Ying","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Carsten","family":"Rother","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,11,24]]},"reference":[{"key":"66_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-319-10584-0_22","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Agrawal","year":"2014","unstructured":"Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 329\u2013344. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10584-0_22"},{"issue":"11","key":"66_CR2","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1109\/TPAMI.2013.54","volume":"35","author":"V Badrinarayanan","year":"2013","unstructured":"Badrinarayanan, V., Budvytis, I., Cipolla, R.: Semi-supervised video segmentation using tree structured graphical models. PAMI 35(11), 2751\u20132764 (2013)","journal-title":"PAMI"},{"issue":"1","key":"66_CR3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s11263-013-0673-5","volume":"110","author":"V Badrinarayanan","year":"2014","unstructured":"Badrinarayanan, V., Budvytis, I., Cipolla, R.: Mixture of trees probabilistic graphical model for video segmentation. IJCV 110(1), 14\u201329 (2014)","journal-title":"IJCV"},{"key":"66_CR4","doi-asserted-by":"crossref","unstructured":"Badrinarayanan, V., Galasso, F., Cipolla, R.: Label propagation in video sequences. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"66_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-540-88682-2_5","volume-title":"Computer Vision \u2013 ECCV 2008","author":"GJ Brostow","year":"2008","unstructured":"Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 44\u201357. Springer, Heidelberg (2008). doi:\n                      10.1007\/978-3-540-88682-2_5"},{"key":"66_CR6","doi-asserted-by":"crossref","unstructured":"Chen, A.Y.C., Corso, J.J.: Propagating multi-class pixel labels throughout video frames. In: WNYIPW (2010)","DOI":"10.1109\/WNYIPW.2010.5649773"},{"key":"66_CR7","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":"66_CR8","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS, pp. 2366\u20132374 (2014)"},{"issue":"2","key":"66_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"66_CR10","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Zhang, G., Shi, J.: Video segmentation by tracing discontinuities in a trajectory embedding. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247883"},{"key":"66_CR11","doi-asserted-by":"crossref","unstructured":"Giordano, D., Murabito, F., Palazzo, S., Spampinato, C.: Superpixel-based video object segmentation using perceptual organization and location prior. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299114"},{"key":"66_CR12","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":"66_CR13","doi-asserted-by":"crossref","unstructured":"Godec, M., Roth, P.M., Bischof, H.: Hough-based tracking of non-rigid objects. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126228"},{"key":"66_CR14","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, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10584-0_23"},{"key":"66_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-642-33863-2_20","volume-title":"Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations","author":"G Hartmann","year":"2012","unstructured":"Hartmann, G., et al.: Weakly supervised learning of object segmentations from web-scale video. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 198\u2013208. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33863-2_20"},{"key":"66_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1007\/978-3-319-10593-2_43","volume-title":"Computer Vision \u2013 ECCV 2014","author":"SD Jain","year":"2014","unstructured":"Jain, S.D., Grauman, K.: Supervoxel-consistent foreground propagation in video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 656\u2013671. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10593-2_43"},{"key":"66_CR17","unstructured":"Johnson, R., Zhang, T.: Semi-supervised convolutional neural networks for text categorization via region embedding. In: NIPS (2015)"},{"key":"66_CR18","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS, pp. 109\u2013117 (2011)"},{"key":"66_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"66_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/978-3-319-10599-4_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Kundu","year":"2014","unstructured":"Kundu, A., Li, Y., Dellaert, F., Li, F., Rehg, J.M.: Joint semantic segmentation and 3D reconstruction from monocular video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 703\u2013718. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10599-4_45"},{"key":"66_CR21","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"66_CR22","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"66_CR23","doi-asserted-by":"crossref","unstructured":"Liu, B., He, X.: Multiclass semantic video segmentation with object-level active inference. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299057"},{"key":"66_CR24","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"66_CR25","doi-asserted-by":"crossref","unstructured":"Mobahi, H., Collobert, R., Weston, J.: Deep learning from temporal coherence in video. In: ICML (2009)","DOI":"10.1145\/1553374.1553469"},{"key":"66_CR26","doi-asserted-by":"crossref","unstructured":"Nagaraja, N.S., Schmidt, F.R., Brox, T.: Video segmentation with just a few strokes. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.370"},{"key":"66_CR27","doi-asserted-by":"crossref","unstructured":"Ochs, P., Brox, T.: Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"66_CR28","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR, pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"66_CR29","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.203"},{"key":"66_CR30","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"66_CR31","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.209"},{"key":"66_CR32","unstructured":"Pinheiro, P., Collobert, R.: Recurrent convolutional neural networks for scene labeling. In: ICML (2014)"},{"key":"66_CR33","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). doi:\n                      10.1007\/978-3-642-33715-4_54"},{"key":"66_CR34","doi-asserted-by":"crossref","unstructured":"Tang, K., Sukthankar, R., Yagnik, J., Fei-Fei, L.: Discriminative segment annotation in weakly labeled video. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.321"},{"key":"66_CR35","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: Human pose estimation via deep neural networks. In: CVPR, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"66_CR36","doi-asserted-by":"crossref","unstructured":"Wu, Z., Li, F., Sukthankar, R., Rehg, J.M.: Robust video segment proposals with painless occlusion handling. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299047"},{"key":"66_CR37","unstructured":"Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: CVPR (2015)"},{"key":"66_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Y., Sundaramoorthi, G., Soatto, S.: Self-occlusions and disocclusions in causal video object segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.501"},{"key":"66_CR39","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C.J., Larochelle, H., Courville, A.C.: Describing videos by exploiting temporal structure. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"66_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.87"},{"key":"66_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"N Zhang","year":"2014","unstructured":"Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 834\u2013849. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10590-1_54"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49409-8_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:35:15Z","timestamp":1602293715000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49409-8_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319494081","9783319494098"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49409-8_66","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":"24 November 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"}]}}