{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:39:41Z","timestamp":1786113581352,"version":"3.56.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585358","type":"print"},{"value":"9783030585365","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58536-5_46","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T23:02:42Z","timestamp":1604358162000},"page":"777-794","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":115,"title":["Learning What to Learn for Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Goutam","family":"Bhat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix J\u00e4remo","family":"Lawin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Danelljan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Felsberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"46_CR1","doi-asserted-by":"crossref","unstructured":"Behl, H.S., Najafi, M., Arnab, A., Torr, P.H.S.: Meta learning deep visual words for fast video object segmentation. In: NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving (2018)","DOI":"10.1109\/IROS45743.2020.9341737"},{"key":"46_CR2","doi-asserted-by":"crossref","unstructured":"Berman, M., Rannen Triki, A., Blaschko, M.B.: The lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4413\u20134421 (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"46_CR3","unstructured":"Bertinetto, L., Henriques, J.F., Torr, P., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: International Conference on Learning Representations (2019)"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van Gool, L., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"46_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: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5320\u20135329. IEEE (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Choi, J., Kwon, J., Lee, K.M.: Deep meta learning for real-time target-aware visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 911\u2013920 (2019)","DOI":"10.1109\/ICCV.2019.00100"},{"key":"46_CR7","doi-asserted-by":"crossref","unstructured":"Cohen, I., Medioni, G.: Detecting and tracking moving objects for video surveillance. In: Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), vol. 2, pp. 319\u2013325. IEEE (1999)","DOI":"10.1109\/CVPR.1999.784651"},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Van Gool, L., Timofte, R.: Probabilistic regression for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"Erd\u00e9lyi, A., Bar\u00e1t, T., Valet, P., Winkler, T., Rinner, B.: Adaptive cartooning for privacy protection in camera networks. In: 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 44\u201349. IEEE (2014)","DOI":"10.1109\/AVSS.2014.6918642"},{"key":"46_CR10","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1126\u20131135. JMLR. org (2017)"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask r-cnn. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"46_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Hu, P., Wang, G., Kong, X., Kuen, J., Tan, Y.P.: Motion-guided cascaded refinement network for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1400\u20131409 (2018)","DOI":"10.1109\/CVPR.2018.00152"},{"key":"46_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-030-01237-3_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y-T Hu","year":"2018","unstructured":"Hu, Y.-T., Huang, J.-B., Schwing, A.G.: VideoMatch: matching based video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 56\u201373. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_4"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Johnander, J., Danelljan, M., Brissman, E., Khan, F.S., Felsberg, M.: A generative appearance model for end-to-end video object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00916"},{"key":"46_CR16","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014"},{"key":"46_CR17","doi-asserted-by":"crossref","unstructured":"Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01091"},{"key":"46_CR18","doi-asserted-by":"crossref","unstructured":"Lin, H., Qi, X., Jia, J.: Agss-vos: attention guided single-shot video object segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3949\u20133957 (2019)","DOI":"10.1109\/ICCV.2019.00405"},{"key":"46_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, L., Zhang, H., Rezatofighi, H., Reid, I.: Meta learning with differentiable closed-form solver for fast video object segmentation. arXiv preprint arXiv:1909.13046 (2019)","DOI":"10.1109\/IROS45743.2020.9341282"},{"key":"46_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/978-3-030-20870-7_35","volume-title":"Computer Vision \u2013 ACCV 2018","author":"J Luiten","year":"2019","unstructured":"Luiten, J., Voigtlaender, P., Leibe, B.: PReMVOS: proposal-generation, refinement and merging for video object segmentation. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 565\u2013580. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_35"},{"issue":"6","key":"46_CR22","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2018.2838670","volume":"41","author":"KK Maninis","year":"2018","unstructured":"Maninis, K.K., et al.: Video object segmentation without temporal information. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 41(6), 1515\u20131530 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"46_CR23","unstructured":"Massa, F., Girshick, R.: maskrcnn-benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch. https:\/\/github.com\/facebookresearch\/maskrcnn-benchmark (2018). Accessed 04 Sep 2019"},{"key":"46_CR24","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7376\u20137385. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"46_CR25","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"46_CR26","doi-asserted-by":"crossref","unstructured":"Park, E., Berg, A.C.: Meta-tracker: fast and robust online adaptation for visual object trackers. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 569\u2013585 (2018)","DOI":"10.1007\/978-3-030-01219-9_35"},{"key":"46_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: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"46_CR28","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., 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, pp. 2663\u20132672 (2017)","DOI":"10.1109\/CVPR.2017.372"},{"key":"46_CR29","doi-asserted-by":"crossref","unstructured":"Robinson, A., Lawin, F.J., Danelljan, M., Khan, F.S., Felsberg, M.: Learning fast and robust target models for video object segmentation (2020)","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"46_CR30","doi-asserted-by":"crossref","unstructured":"Ros, G., Ramos, S., Granados, M., Bakhtiary, A., Vazquez, D., Lopez, A.M.: Vision-based offline-online perception paradigm for autonomous driving. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 231\u2013238. IEEE (2015)","DOI":"10.1109\/WACV.2015.38"},{"key":"46_CR31","doi-asserted-by":"crossref","unstructured":"Saleh, K., Hossny, M., Nahavandi, S.: Kangaroo vehicle collision detection using deep semantic segmentation convolutional neural network. In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20137. IEEE (2016)","DOI":"10.1109\/DICTA.2016.7797057"},{"key":"46_CR32","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":"46_CR33","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Leibe, B.: Feelvos: fast end-to-end embedding learning for video object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"46_CR34","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P.H., Leibe, B.: Siam r-cnn: visual tracking by re-detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"46_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-01261-8_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Vondrick","year":"2018","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 402\u2013419. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_24"},{"key":"46_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1328\u20131338 (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"46_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, J., Liu, L., Zhu, F., Shao, L.: Ranet: ranking attention network for fast video object segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3978\u20133987 (2019)","DOI":"10.1109\/ICCV.2019.00408"},{"key":"46_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-3-030-01228-1_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Xu","year":"2018","unstructured":"Xu, N., et al.: YouTube-VOS: sequence-to-sequence video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 603\u2013619. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_36"},{"key":"46_CR39","unstructured":"Xu, N., et al.: Youtube-vos: A large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"46_CR40","first-page":"15","volume":"29","author":"L Yang","year":"2018","unstructured":"Yang, L., Wang, Y., Xiong, X., Yang, J., Katsaggelos, A.K.: Efficient video object segmentation via network modulation. Algorithms 29, 15 (2018)","journal-title":"Algorithms"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58536-5_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:48:06Z","timestamp":1730594886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58536-5_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585358","9783030585365"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58536-5_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}