{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:34:24Z","timestamp":1769639664039,"version":"3.49.0"},"publisher-location":"Cham","reference-count":41,"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_6","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:23:51Z","timestamp":1538835831000},"page":"93-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":127,"title":["Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0376-5135","authenticated-orcid":false,"given":"Xiaoxiao","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"6_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: ICLR (2015)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"6_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)","DOI":"10.1109\/CVPR.2017.565"},{"key":"6_CR4","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 (2015)"},{"key":"6_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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11263-006-7899-4","volume":"70","author":"PF Felzenszwalb","year":"2006","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. IJCV 70(1), 41\u201354 (2006)","journal-title":"IJCV"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"6_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","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. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Hui, T.W., Tang, X., Loy, C.C.: LiteFlowNet: a lightweight convolutional neural network for optical flow estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00936"},{"key":"6_CR13","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"6_CR14","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, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_43"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Jampani, V., Gadde, R., Gehler, P.V.: Video propagation networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.336"},{"key":"6_CR16","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for object tracking. In: CVPRW (2017)"},{"key":"6_CR17","unstructured":"Le, T.N., et al.: Instance re-identification flow for video object segmentation. In: CVPRW (2017)"},{"key":"6_CR18","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":"6_CR19","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":"6_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, Z., Luo, P., Loy, C.C., Tang, X.: Not all pixels are equal: difficulty-aware semantic segmentation via deep layer cascade. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.684"},{"key":"6_CR21","unstructured":"Li, X., et al.: Video object segmentation with re-identification. In: CVPRW (2017)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.472"},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1109\/TPAMI.2017.2737535","volume":"40","author":"Z Liu","year":"2017","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Deep learning Markov random field for semantic segmentation. TPAMI 40, 1814\u20131828 (2017)","journal-title":"TPAMI"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"M\u00e4rki, N., Perazzi, F., Wang, O., Sorkine-Hornung, A.: Bilateral space video segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.87"},{"key":"6_CR25","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":"6_CR26","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"6_CR27","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"6_CR28","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 Davis challenge on video object segmentation. arXiv:1704.00675 (2017)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"6_CR30","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Yang, M.H., Black, M.J.: Video segmentation via object flow. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.423"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J.F., Vedaldi, A., Torr, P.H.: End-to-end representation learning for correlation filter based tracking (2017)","DOI":"10.1109\/CVPR.2017.531"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)","DOI":"10.5244\/C.31.116"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Xiao, F., Jae Lee, Y.: Track and segment: an iterative unsupervised approach for video object proposals. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.107"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.360"},{"key":"6_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-642-33783-3_45","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C Xu","year":"2012","unstructured":"Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 626\u2013639. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_45"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"6_CR39","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: CVPR (2017)","DOI":"10.1109\/ICCV.2017.238"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.179"}],"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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T01:01:47Z","timestamp":1665018107000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_6","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"}]}}