{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:59:38Z","timestamp":1769637578363,"version":"3.49.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","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\/978-3-030-58601-0_18","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"293-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["ScribbleBox: Interactive Annotation Framework for Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Bowen","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyue","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Acuna, D., Ling, H., Kar, A., Fidler, S.: Efficient interactive annotation of segmentation datasets with Polygon-RNN++. In CVPR (2018)","DOI":"10.1109\/CVPR.2018.00096"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bai, X., Sapiro, G.: A geodesic framework for fast interactive image and video segmentation and matting. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, Rio de Janeiro, Brazil, 14\u201320 October 2007, pp. 1\u20138. IEEE Computer Society (2007)","DOI":"10.1109\/ICCV.2007.4408931"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Bai, X., Wang, J., Simons, D., Sapiro, G.: Video SnapCut: robust video object cutout using localized classifiers. ACM Trans. Graph. 28(3) (2009). Article no. 70","DOI":"10.1145\/1531326.1531376"},{"key":"18_CR4","unstructured":"Benard, A., Gygli, M.: Interactive video object segmentation in the wild. ArXiv, abs\/1801.00269 (2018)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., Gool, L.V.: One-shot video object segmentation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 5320\u20135329. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.565"},{"key":"18_CR6","unstructured":"Caelles, S., et al.: The 2018 DAVIS challenge on video object segmentation. arXiv:1803.00557 (2018)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a Polygon-RNN. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.477"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Fidler, S., Yuille, A., Urtasun, R.: Beat the MTurkers: automatic image labeling from weak 3D supervision. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.409"},{"key":"18_CR9","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: Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00130"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the EPIC-KITCHENS dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: The EPIC-KITCHENS dataset: collection, challenges and baselines. IEEE Trans. Pattern Anal. Mach. Intell. (2020)","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"18_CR12","unstructured":"Gao, J., Tang, C., Ganapathi-Subramanian, V., Huang, J., Su, H., Guibas, L.J.: DeepSpline: data-driven reconstruction of parametric curves and surfaces. arXiv preprint arXiv:1901.03781 (2019)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361, June 2012","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Yuen, J., Russell, B., Liu, C., Torralba, A.: LabelMe video: building a video database with human annotations. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1451\u20131458, September 2009","DOI":"10.1109\/ICCV.2009.5459289"},{"key":"18_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-030-20870-7_8","volume-title":"Computer Vision \u2013 ACCV 2018","author":"A Khoreva","year":"2019","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 123\u2013141. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_8"},{"key":"18_CR17","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings (2017)"},{"key":"18_CR18","unstructured":"Levinkov, E., Tompkin, J., Bonneel, N., Kirchhoff, S., Andres, B., Pfister, H.: Interactive multicut video segmentation. In: PG 2016 (2016)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980, June 2018","DOI":"10.1109\/CVPR.2018.00935"},{"issue":"3","key":"18_CR20","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1145\/1073204.1073234","volume":"24","author":"Y Li","year":"2005","unstructured":"Li, Y., Sun, J., Shum, H.: Video object cut and paste. ACM Trans. Graph. 24(3), 595\u2013600 (2005)","journal-title":"ACM Trans. Graph."},{"key":"18_CR21","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":"18_CR22","unstructured":"Lin, Z., Xie, J., Zhou, C., Hu, J., Zheng, W.: Interactive video object segmentation via spatio-temporal context aggregation and online learning. In: The 2019 DAVIS Challenge on Video Object Segmentation - CVPR Workshops (2019)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Ling, H., Gao, J., Kar, A., Chen, W., Fidler, S.: Fast interactive object annotation with Curve-GCN. In: CVPR, June 2019","DOI":"10.1109\/CVPR.2019.00540"},{"key":"18_CR24","unstructured":"Mahadevan, S., Voigtlaender, P., Leibe, B.: Iteratively trained interactive segmentation. arXiv preprint arXiv:1805.04398 (2018)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Manen, S., Gygli, M., Dai, D., Van Gool, L.: PathTrack: fast trajectory annotation with path supervision. arXiv:1703.02437 (2017)","DOI":"10.1109\/ICCV.2017.40"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Maninis, K.-K., Caelles, S., Pont-Tuset, J., Van Gool, L.: Deep extreme cut: from extreme points to object segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00071"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Mortensen, E.N., Barrett, W.A.: Intelligent scissors for image composition. In: SIGGRAPH, pp. 191\u2013198 (1995)","DOI":"10.1145\/218380.218442"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Nagaraja, N.S., Schmidt, F.R., Brox, T.: Video segmentation with just a few strokes. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015, pp. 3235\u20133243. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.370"},{"key":"18_CR29","unstructured":"Najafi, M., Kulharia, V., Ajanthan, T., Torr, P.H.S.: Similarity learning for dense label transfer. In: The 2018 DAVIS Challenge on Video Object Segmentation - CVPR Workshops (2018)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.-Y., Xu, N., Kim, S.J.: Fast user-guided video object segmentation by interaction-and-propagation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5247\u20135256 (2019)","DOI":"10.1109\/CVPR.2019.00539"},{"key":"18_CR31","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, pp. 9226\u20139235 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"18_CR32","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: IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, 27 September\u20134 October 2009, pp. 779\u2013786. IEEE Computer Society (2009)","DOI":"10.1109\/ICCV.2009.5459293"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. In: SIGGRAPH (2004)","DOI":"10.1145\/1186562.1015720"},{"issue":"3","key":"18_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.158"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"issue":"1","key":"18_CR37","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s11263-012-0564-1","volume":"101","author":"C Vondrick","year":"2013","unstructured":"Vondrick, C., Patterson, D., Ramanan, D.: Efficiently scaling up crowdsourced video annotation. Int. J. Comput. Vis. 101(1), 184\u2013204 (2013). https:\/\/doi.org\/10.1007\/s11263-012-0564-1","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR38","unstructured":"Vondrick, C., Ramanan, D.: Video annotation and tracking with active learning. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, NIPS 2011, USA, pp. 28\u201336. Curran Associates Inc. (2011)"},{"issue":"3","key":"18_CR39","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1145\/1073204.1073233","volume":"24","author":"J Wang","year":"2005","unstructured":"Wang, J., Bhat, P., Colburn, A., Agrawala, M., Cohen, M.F.: Interactive video cutout. ACM Trans. Graph. 24(3), 585\u2013594 (2005)","journal-title":"ACM Trans. Graph."},{"key":"18_CR40","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ling, H., Acuna, D., Kar, A., Fidler, S.: Object instance annotation with deep extreme level set evolution. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00768"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Wug Oh, S., Lee, J.-Y., Sunkavalli, K., Joo Kim, S.: Fast video object segmentation by reference-guided mask propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7376\u20137385 (2018)","DOI":"10.1109\/CVPR.2018.00770"},{"key":"18_CR43","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"}],"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\/978-3-030-58601-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:08:46Z","timestamp":1732666126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_18","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":"28 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)"}}]}}