{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:46:00Z","timestamp":1775245560404,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012182","type":"print"},{"value":"9783030012199","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\/978-3-030-01219-9_13","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T10:23:51Z","timestamp":1538821431000},"page":"215-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":101,"title":["Unsupervised Video Object Segmentation with Motion-Based Bilateral Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5991-649X","authenticated-orcid":false,"given":"Siyang","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6081-8347","authenticated-orcid":false,"given":"Bryan","family":"Seybold","sequence":"additional","affiliation":[]},{"given":"Alexey","family":"Vorobyov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2335-4445","authenticated-orcid":false,"given":"Xuejing","family":"Lei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9474-5035","authenticated-orcid":false,"given":"C.-C. Jay","family":"Kuo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Adams, A., Baek, J., Davis, M.A.: Fast high-dimensional filtering using the permutohedral lattice. In: Computer Graphics Forum, vol. 29, pp. 753\u2013762. Wiley Online Library (2010)","DOI":"10.1111\/j.1467-8659.2009.01645.x"},{"issue":"3","key":"13_CR2","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","volume":"33","author":"T Brox","year":"2011","unstructured":"Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. 33(3), 500\u2013513 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR 2017. IEEE (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"13_CR4","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., L. Yuille, A.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. (2016)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"De Brabandere, B., Neven, D., Van Gool, L.: Semantic instance segmentation with a discriminative loss function. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) (2017)","DOI":"10.1109\/CVPRW.2017.66"},{"issue":"2","key":"13_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. (IJCV) 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC, vol. 2, p. 8 (2014)","DOI":"10.5244\/C.28.21"},{"key":"13_CR9","unstructured":"Fathi, A., et al.: Semantic instance segmentation via deep metric learning. arXiv preprint arXiv:1703.10277 (2017)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"13_CR11","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.757"},{"key":"13_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-3-540-88682-2_4","volume-title":"Computer Vision \u2013 ECCV 2008","author":"G Heitz","year":"2008","unstructured":"Heitz, G., Koller, D.: Learning spatial context: using stuff to find things. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 30\u201343. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_4"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xia, C., Li, S., Wang, Y., Song, Y., Kuo, C.C.J.: Unsupervised clustering guided semantic segmentation. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00167"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Semantic segmentation with reverse attention. In: British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.18"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Jampani, V., Gadde, R., Gehler, P.V.: Video propagation networks. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.336"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Jampani, V., Kiefel, M., Gehler, P.V.: Learning sparse high dimensional filters: Image filtering, dense CRFs and bilateral neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4452\u20134461 (2016)","DOI":"10.1109\/CVPR.2016.482"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Kim, C.S.: Online video object segmentation via convolutional trident network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5849\u20135858 (2017)","DOI":"10.1109\/CVPR.2017.790"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Keuper, M., Andres, B., Brox, T.: Motion trajectory segmentation via minimum cost multicuts. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3271\u20133279 (2015)","DOI":"10.1109\/ICCV.2015.374"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Perazzi, F., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Koh, Y.J., Kim, C.S.: Primary object segmentation in videos based on region augmentation and reduction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.784"},{"key":"13_CR23","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109\u2013117 (2011)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Seybold, B., Vorobyov, A., Fathi, A., Huang, Q., Kuo, C.C.J.: Instance embedding transfer to unsupervised video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00683"},{"key":"13_CR25","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":"13_CR26","doi-asserted-by":"crossref","unstructured":"M\u00e4rki, N., Perazzi, F., Wang, O., Sorkine-Hornung, A.: Bilateral space video segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 743\u2013751 (2016)","DOI":"10.1109\/CVPR.2016.87"},{"issue":"6","key":"13_CR27","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TPAMI.2013.242","volume":"36","author":"P Ochs","year":"2014","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187\u20131200 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1777\u20131784 (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Taylor, B., Karasev, V., Soatto, S.: Causal video object segmentation from persistence of occlusions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4268\u20134276 (2015)","DOI":"10.1109\/CVPR.2015.7299055"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.64"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: 1998 Sixth International Conference on Computer Vision, pp. 839\u2013846. IEEE (1998)","DOI":"10.1109\/ICCV.1998.710815"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Yang, M.H., Black, M.J.: Video segmentation via object flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3899\u20133908 (2016)","DOI":"10.1109\/CVPR.2016.423"},{"key":"13_CR35","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-Net: learning of structure and motion from video. arXiv preprint arXiv:1704.07804 (2017)"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.116"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Yoon, J.S., Rameau, F., Kim, J., Lee, S., Shin, S., Kweon, I.S.: Pixel-level matching for video object segmentation using convolutional neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2186\u20132195. IEEE (2017)","DOI":"10.1109\/ICCV.2017.238"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"}],"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\/978-3-030-01219-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:47:07Z","timestamp":1775242027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_13","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":"7 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"}]}}