{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T08:03:00Z","timestamp":1790928180067,"version":"4.1.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012366","type":"print"},{"value":"9783030012373","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\/978-3-030-01237-3_4","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T18:42:18Z","timestamp":1538851338000},"page":"56-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":176,"title":["VideoMatch: Matching Based Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Yuan-Ting","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Bin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander G.","family":"Schwing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Avinash Ramakanth, S., Venkatesh Babu, R.: SeamSeg: video object segmentation using patch seams. In: Proceedings of CVPR (2014)","DOI":"10.1109\/CVPR.2014.55"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bai, X., Wang, J., Simons, D., Sapiro, G.: Video snapcut: robust video object cutout using localized classifiers. In: SIGGRAPH (2009)","DOI":"10.1145\/1576246.1531376"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional siamese networks for object tracking. In: Proceedings of CVPR (2017)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Caelles, S., Chen, Y., Pont-Tuset, J., Van Gool, L.: Semantically-guided video object segmentation (2017). arXiv preprint: arXiv:1704.01926","DOI":"10.1109\/CVPR.2017.565"},{"key":"4_CR5","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: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"4_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. PAMI 40, 834\u2013848 (2018)","journal-title":"PAMI"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pont-Tuset, J., Montes, A., Van Gool, L.: Blazingly fast video object segmentation with pixel-wise metric learning. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00130"},{"key":"4_CR8","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: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.81"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, J., Tsai, Y.H., Hung, W.C., Wang, S., Yang, M.H.: Fast and accurate online video object segmentation via tracking parts. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00774"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"4_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2015)","journal-title":"IJCV"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC (2014)","DOI":"10.5244\/C.28.21"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Q., Zhong, F., Lischinski, D., Cohen-Or, D., Chen, B.: JumpCut: non-successive mask transfer and interpolation for video cutout. In: SIGGRAPH (2015)","DOI":"10.1145\/2816795.2818105"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Godec, M., Roth, P.M., Bischof, H.: Hough-based tracking of non-rigid objects. In: Proceedings of ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126228"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: Proceedings of ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR18","first-page":"5995","volume":"24","author":"YT Hu","year":"2015","unstructured":"Hu, Y.T., Lin, Y.Y., Chen, H.Y., Hsu, K.J., Chen, B.Y.: Matching images with multiple descriptors: an unsupervised approach for locally adaptive descriptor selection. TIP 24, 5995\u20136010 (2015)","journal-title":"TIP"},{"key":"4_CR19","unstructured":"Hu, Y.T., Huang, J.B., Schwing, A.: MaskRNN: instance level video object segmentation. In: NIPS (2017)"},{"key":"4_CR20","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/978-3-030-01246-5_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Yuan-Ting Hu","year":"2018","unstructured":"Hu, Y.T., Huang, J.B., Schwing, A.: Unsupervised video object segmentation using motion saliency-guided spatio-temporal propagation. In: Ferrari, V., et al. (eds.) ECCV 2018, Part VIII. LNCS, vol. 11205, pp. 813\u2013830. Springer, Cham (2018)"},{"key":"4_CR21","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, Part IV. LNCS, vol. 8692, pp. 656\u2013671. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_43"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmention of generic objects in videos. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Jampani, V., Gadde, R., Gehler, P.V.: Video propagation networks. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.336"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Kim, C.S.: Online video object segmentation via convolutional trident network. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.790"},{"key":"4_CR25","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 CVPR (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"4_CR26","unstructured":"Khoreva, A., Benenson, R., Ilg, E., Brox, T., Schiele, B.: Lucid data dreaming for object tracking (2017). arXiv preprint: arXiv:1703.09554"},{"key":"4_CR27","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)"},{"key":"4_CR28","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., et al.: A novel performance evaluation methodology for single-target trackers. PAMI 38, 2137\u20132155 (2016)","journal-title":"PAMI"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: Proceedings of ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Lezama, J., Alahari, K., Sivic, J., Laptev, I.: Track to the future: spatio-temporal video segmentation with long-range motion cues. In: Proceedings of CVPR (2011)","DOI":"10.1109\/CVPR.2011.6044588"},{"key":"4_CR31","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: Proceedings of ICCV (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"4_CR32","unstructured":"Li, X., et al.: Video object segmentation with re-identification. In: The 2017 DAVIS Challenge on Video Object Segmentation - CVPR Workshops (2017)"},{"key":"4_CR33","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Maerki, N., Perazzi, F., Wang, O., Sorkine-Hornung, A.: Bilateral space video segmentation. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.87"},{"key":"4_CR35","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1615\u20131630 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Nagaraja, N., Schmidt, F., Brox, T.: Video segmentation with just a few strokes. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.370"},{"key":"4_CR37","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. PAMI 36, 1187\u20131200 (2014)","journal-title":"PAMI"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Sunkavalli, K., Kim, S.J.: Fast video object segmentation by reference-guided mask propagation. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: Proceedings of ICCV (2013)","DOI":"10.1109\/ICCV.2013.223"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Gool, L.V., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.369"},{"key":"4_CR42","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 (2017). arXiv preprint: arXiv:1704.00675"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: Proceedings of CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Price, B.L., Morse, B.S., Cohen, S.: LIVEcut: learning-based interactive video segmentation by evaluation of multiple propagated cues. In: Proceedings of ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459293"},{"key":"4_CR45","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-016-0908-3","volume":"120","author":"J Revaud","year":"2016","unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Deepmatching: hierarchical deformable dense matching. IJCV 120, 300\u2013323 (2016)","journal-title":"IJCV"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.64"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.480"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Tsai, D., Flagg, M., Rehg, J.: Motion coherent tracking with multi-label MRF optimization. In: Proceedings of BMVC (2010)","DOI":"10.5244\/C.24.56"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Yang, M.H., Black, M.J.: Video segmentation via object flow. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.423"},{"key":"4_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1007\/978-3-642-33715-4_36","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S Vijayanarasimhan","year":"2012","unstructured":"Vijayanarasimhan, S., Grauman, K.: Active frame selection for label propagation in videos. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 496\u2013509. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_36"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for the 2017 DAVIS challenge on video object segmentation. In: The 2017 DAVIS Challenge on Video Object Segmentation - CVPR Workshops (2017)","DOI":"10.5244\/C.31.116"},{"key":"4_CR53","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":"4_CR54","first-page":"5645","volume":"26","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., Porikli, F.: Selective video object cutout. TIP 26, 5645\u20135655 (2017)","journal-title":"TIP"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Xiao, F., Lee, Y.J.: Track and segment: an iterative unsupervised approach for video object proposals. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.107"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, Y., Xiong, X., Yang, J., Katsaggelos, A.K.: Efficient video object segmentation via network modulation. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00680"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Yang, T.Y., Hsu, J.H., Lin, Y.Y., Chuang, Y.Y.: DeepCD: learning deep complementary descriptors for patch representations. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.359"},{"key":"4_CR58","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/1177352.1177355","volume":"38","author":"A Yilmaz","year":"2006","unstructured":"Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38, 13 (2006)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"4_CR59","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: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.238"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Zhong, F., Qin, X., Peng, Q., Meng, X.: Discontinuity-aware video object cutout. In: SIGGRAPH (2012)","DOI":"10.1145\/2366145.2366194"}],"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\/978-3-030-01237-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:04:59Z","timestamp":1665014699000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01237-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012366","9783030012373"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01237-3_4","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"}]}}