{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:17:16Z","timestamp":1752671836978,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319464534"},{"type":"electronic","value":"9783319464541"}],"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_19","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:15:09Z","timestamp":1473930909000},"page":"302-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Recurrent Temporal Deep Field for Semantic Video Labeling"],"prefix":"10.1007","author":[{"given":"Peng","family":"Lei","sequence":"first","affiliation":[]},{"given":"Sinisa","family":"Todorovic","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: CVPR (2011)","key":"19_CR1","DOI":"10.1109\/CVPR.2011.5995566"},{"unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)","key":"19_CR2"},{"unstructured":"Sutskever, I., Hinton, G.E., Taylor, G.W.: The recurrent temporal restricted Boltzmann machine. In: NIPS (2009)","key":"19_CR3"},{"unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)","key":"19_CR4"},{"doi-asserted-by":"crossref","unstructured":"Galmar, E., Athanasiadis, T., Huet, B., Avrithis, Y.: Spatiotemporal semantic video segmentation. In: MSPW (2008)","key":"19_CR5","DOI":"10.1109\/MMSP.2008.4665143"},{"doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)","key":"19_CR6","DOI":"10.1109\/CVPR.2010.5539893"},{"doi-asserted-by":"crossref","unstructured":"Jain, A., Chatterjee, S., Vidal, R.: Coarse-to-fine semantic video segmentation using supervoxel trees. In: ICCV (2013)","key":"19_CR7","DOI":"10.1109\/ICCV.2013.234"},{"doi-asserted-by":"crossref","unstructured":"Yi, S., Pavlovic, V.: Multi-cue structure preserving mrf for unconstrained video segmentation. arXiv preprint arXiv:1506.09124 (2015)","key":"19_CR8","DOI":"10.1109\/ICCV.2015.373"},{"unstructured":"Zhao, H., Fu, Y.: Semantic single video segmentation with robust graph representation. In: IJCAI (2015)","key":"19_CR9"},{"doi-asserted-by":"crossref","unstructured":"Liu, B., He, X., Gould, S.: Multi-class semantic video segmentation with exemplar-based object reasoning. In: WACV (2015)","key":"19_CR10","DOI":"10.1109\/WACV.2015.140"},{"issue":"8","key":"19_CR11","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. PAMI 35(8), 1915\u20131929 (2013)","journal-title":"PAMI"},{"doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","key":"19_CR12","DOI":"10.1109\/CVPR.2015.7298965"},{"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":"19_CR13"},{"unstructured":"Ciresan, D., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Deep neural networks segment neuronal membranes in electron microscopy images. In: NIPS (2012)","key":"19_CR14"},{"unstructured":"Pinheiro, P.H., Collobert, R.: Recurrent convolutional neural networks for scene parsing. In: ICML (2014)","key":"19_CR15"},{"key":"19_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 297\u2013312. Springer, Heidelberg (2014)"},{"key":"19_CR17","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":"19_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-319-16808-1_36","volume-title":"Computer Vision \u2013 ACCV 2014","author":"Y Ganin","year":"2015","unstructured":"Ganin, Y., Lempitsky, V.: $$N^4$$-fields: neural network nearest neighbor fields for image transforms. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 536\u2013551. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-16808-1_36"},{"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: ICCV (2015)","key":"19_CR19","DOI":"10.1109\/ICCV.2015.179"},{"doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV (2015)","key":"19_CR20","DOI":"10.1109\/ICCV.2015.178"},{"key":"19_CR21","volume-title":"Information Processing in Dynamical Systems: Foundations of Harmony Theory","author":"P Smolensky","year":"1986","unstructured":"Smolensky, P.: Information Processing in Dynamical Systems: Foundations of Harmony Theory. MIT Press Cambridge, Cambridge (1986)"},{"unstructured":"He, X., Zemel, R.S., Carreira-Perpi\u00f1\u00e1n, M.\u00c1: Multiscale conditional random fields for image labeling. In: CVPR (2004)","key":"19_CR22"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Tarlow, D., Zemel, R.: Exploring compositional high order pattern potentials for structured output learning. In: CVPR (2013)","key":"19_CR23","DOI":"10.1109\/CVPR.2013.14"},{"doi-asserted-by":"crossref","unstructured":"Kae, A., Sohn, K., Lee, H., Learned-Miller, E.: Augmenting CRFs with boltzmann machine shape priors for image labeling. In: CVPR (2013)","key":"19_CR24","DOI":"10.1109\/CVPR.2013.263"},{"issue":"2","key":"19_CR25","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-013-0669-1","volume":"107","author":"SA Eslami","year":"2014","unstructured":"Eslami, S.A., Heess, N., Williams, C.K., Winn, J.: The shape Boltzmann machine: a strong model of object shape. IJCV 107(2), 155\u2013176 (2014)","journal-title":"IJCV"},{"doi-asserted-by":"crossref","unstructured":"Kae, A., Marlin, B., Learned-Miller, E.: The shape-time random field for semantic video labeling. In: CVPR (2014)","key":"19_CR26","DOI":"10.1109\/CVPR.2014.42"},{"doi-asserted-by":"crossref","unstructured":"Taylor, G.W., Hinton, G.E., Roweis, S.T.: Modeling human motion using binary latent variables. In: NIPS (2006)","key":"19_CR27","DOI":"10.7551\/mitpress\/7503.003.0173"},{"doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Technical report, DTIC Document (1985)","key":"19_CR28","DOI":"10.21236\/ADA164453"},{"issue":"8","key":"19_CR29","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771\u20131800 (2002)","journal-title":"Neural Comput."},{"unstructured":"Mnih, V., Larochelle, H., Hinton, G.E.: Conditional restricted Boltzmann machines for structured output prediction. In: UAI (2011)","key":"19_CR30"},{"doi-asserted-by":"crossref","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. In: Predicting Structured Data, vol. 1 (2006)","key":"19_CR31","DOI":"10.7551\/mitpress\/7443.003.0014"},{"issue":"2","key":"19_CR32","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2008","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. PRL 30(2), 88\u201397 (2008)","journal-title":"PRL"},{"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)","key":"19_CR33","DOI":"10.1109\/ICCV.2013.273"},{"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)","key":"19_CR34","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"19_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-642-15555-0_21","volume-title":"Computer Vision \u2013 ECCV 2010","author":"T Brox","year":"2010","unstructured":"Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 282\u2013295. Springer, Heidelberg (2010)"},{"key":"19_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1007\/978-3-642-15561-1_51","volume-title":"Computer Vision \u2013 ECCV 2010","author":"C Zhang","year":"2010","unstructured":"Zhang, C., Wang, L., Yang, R.: Semantic segmentation of urban scenes using dense depth maps. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 708\u2013721. Springer, Heidelberg (2010)"},{"issue":"2","key":"19_CR37","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/s11263-012-0574-z","volume":"101","author":"J Tighe","year":"2013","unstructured":"Tighe, J., Lazebnik, S.: Superparsing. IJCV 101(2), 329\u2013349 (2013)","journal-title":"IJCV"},{"doi-asserted-by":"crossref","unstructured":"Sturgess, P., Alahari, K., Ladicky, L., Torr, P.H.: Combining appearance and structure from motion features for road scene understanding. In: BMVC (2009)","key":"19_CR38","DOI":"10.5244\/C.23.62"},{"key":"19_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-642-15561-1_31","volume-title":"Computer Vision \u2013 ECCV 2010","author":"\u013d Ladick\u00fd","year":"2010","unstructured":"Ladick\u00fd, \u013d., Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, where and how many? combining object detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 424\u2013437. Springer, Heidelberg (2010)"},{"doi-asserted-by":"crossref","unstructured":"Rota Bulo, S., Kontschieder, P.: Neural decision forests for semantic image labelling. In: CVPR (2014)","key":"19_CR40","DOI":"10.1109\/CVPR.2014.18"},{"unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)","key":"19_CR41"}],"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_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T03:56:53Z","timestamp":1692503813000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46454-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464534","9783319464541"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46454-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}]}}