{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:00:30Z","timestamp":1778698830192,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200465","type":"print"},{"value":"9783031200472","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20047-2_31","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T10:02:55Z","timestamp":1666432975000},"page":"534-551","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Towards Sequence-Level Training for\u00a0Visual Tracking"],"prefix":"10.1007","author":[{"given":"Minji","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungkwan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungseul","family":"Ok","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohyung","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"31_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"31_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/978-3-030-01234-2_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Chen","year":"2018","unstructured":"Chen, B., Wang, D., Li, P., Wang, S., Lu, H.: Real-time \u2018Actor-Critic\u2019 tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 328\u2013345. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_20"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R.: Siamese box adaptive network for visual tracking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: accurate tracking by overlap maximization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L.V., Timofte, R.: Probabilistic regression for visual tracking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J., Wang, W., Liu, Y., Shao, L., Porikli, F.: Hyperparameter optimization for tracking with continuous deep q-learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00061"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Henschel, R., Zou, Y., Rosenhahn, B.: Multiple people tracking using body and joint detections. In: CVPR (2019)","DOI":"10.1109\/CVPRW.2019.00105"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep q-learning from demonstrations. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Hu, H.N., et al.: Joint monocular 3d vehicle detection and tracking. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00549"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Huang, C., Lucey, S., Ramanan, D.: Learning policies for adaptive tracking with deep feature cascades. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.21"},{"key":"31_CR16","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. TPAMI. 43, 1562\u20131577 (2019)","journal-title":"TPAMI."},{"key":"31_CR17","unstructured":"III, J.S.S., Ramanan, D.: Tracking as online decision-making: Learning a policy from streaming videos with reinforcement learning. In: ICCV (2017)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Javed, S., Danelljan, M., Khan, F.S., Khan, M.H., Felsberg, M., Matas, J.: Visual object tracking with discriminative filters and Siamese networks: a survey and outlook. arXiv preprint arXiv:2112.02838 (2021)","DOI":"10.1109\/TPAMI.2022.3212594"},{"key":"31_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01225-0_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"I Jung","year":"2018","unstructured":"Jung, I., Son, J., Baek, M., Han, B.: Real-time MDNet. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 89\u2013104. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_6"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Junliang Xing, J.Y.: SiamRPN++: evolution of Siamese visual tracking with very deep networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"31_CR21","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"31_CR22","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":"31_CR23","doi-asserted-by":"crossref","unstructured":"Marvasti-Zadeh, S.M., Cheng, L., Ghanei-Yakhdan, H., Kasaei, S.: Deep learning for visual tracking: a comprehensive survey. IEEE Transactions on Intelligent Transportation Systems (2021)","DOI":"10.1109\/TITS.2020.3046478"},{"key":"31_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/978-3-030-01246-5_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M M\u00fcller","year":"2018","unstructured":"M\u00fcller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 310\u2013327. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_19"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Real, E., Shlens, J., Mazzocchi, S., Pan, X., Vanhoucke, V.: YouTube-boundingboxes: a large high-precision human-annotated data set for object detection in video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.789"},{"key":"31_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-030-01240-3_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Ren","year":"2018","unstructured":"Ren, L., Yuan, X., Lu, J., Yang, M., Zhou, J.: Deep reinforcement learning with iterative shift for visual tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 697\u2013713. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_42"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"31_CR29","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. IJCV. 115, 211\u2013252 (2015)","journal-title":"IJCV."},{"key":"31_CR30","first-page":"1444","volume":"36","author":"AW Smeulders","year":"2013","unstructured":"Smeulders, A.W., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. TPAMI. 36, 1444\u20131468 (2013)","journal-title":"TPAMI."},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Wang, G., Luo, C., Sun, X., Xiong, Z., Zeng, W.: Tracking by instance detection: a meta-learning approach. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00632"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"31_CR33","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"31_CR35","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":"31_CR36","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Z., Li, Z., Yuan, Y., Yu, G.: SiamFC++: towards robust and accurate visual tracking with target estimation guidelines. In: CVPR (2020)","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Yan, B., Zhang, X., Wang, D., Lu, H., Yang, X.: Alpha-Refine: boosting tracking performance by precise bounding box estimation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Yu, Y., Xiong, Y., Huang, W., Scott, M.R.: Deformable Siamese attention networks for visual object tracking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Yun, S., Choi, J., Yoo, Y., Yun, K., Young Choi, J.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.148"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zheng, Z., Jia, R., Li, M.: Visual tracking via hierarchical deep reinforcement learning. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16443"},{"key":"31_CR42","unstructured":"Zhang, W., et al.: Online decision based visual tracking via reinforcement learning. In: NIPS (2020)"},{"key":"31_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/978-3-030-58589-1_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 771\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_46"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Gonzalez-Garcia, A., van de Weijer, J., Danelljan, M., Khan, F.S.: Learning the model update for Siamese trackers. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00411"},{"key":"31_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-030-01240-3_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., et al.: Distractor-aware Siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103\u2013119. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_7"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20047-2_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T23:14:45Z","timestamp":1666739685000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20047-2_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}