{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:31Z","timestamp":1777655791071,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819985548","type":"print"},{"value":"9789819985555","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T00:00:00Z","timestamp":1703721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T00:00:00Z","timestamp":1703721600000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8555-5_10","type":"book-chapter","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T07:02:36Z","timestamp":1703660556000},"page":"120-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["CSTrack: A Comprehensive and Concise Vision Transformer Tracker"],"prefix":"10.1007","author":[{"given":"Yao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lunbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,28]]},"reference":[{"key":"10_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":"10_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: ICCV, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"10_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-030-58592-1_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Bhat","year":"2020","unstructured":"Bhat, G., Danelljan, M., Van Gool, L., Timofte, R.: Know your surroundings: exploiting scene information for object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 205\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_13"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Chen, B., Li, P., Bai, L., Qiao, L., Shen, Q., Li, B.: Backbone is all your need: a simplified architecture for visual object tracking. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13682, pp. 375\u2013392. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_22","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J.: Transformer tracking. In: CVPR, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L.V., Timofte, R.: Probabilistic regression for visual tracking. In: CVPR, pp. 7183\u20137192 (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"10_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Fu, Z., Fu, Z., Liu, Q., Cai, W., Wang, Y.: SparseTT: visual tracking with sparse transformers. In: IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/127"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, Q., Fu, Z., Wang, Y.: STMTrack: template-free visual tracking with space-time memory networks. In: CVPR, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Guo, M., Zhang, Z., Fan, H., Jing, L., Lyu, Y., Li, B.: Learning target-aware representation for visual tracking via informative interactions. In: IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/130"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. In: TPAMI, pp. 1562\u20131577 (2019)","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Kim, M., Lee, S., Ok, J., Han, B., Cho, M.: Towards sequence-level training for visual tracking. In: ECCV, pp. 534\u2013551 (2022)","DOI":"10.1007\/978-3-031-20047-2_31"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of Siamese visual tracking with very deep networks. In: CVPR, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: CVPR, pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"10_CR18","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":"10_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Ma, F., et al.: Unified transformer tracker for object tracking. In: CVPR, pp. 8781\u20138790 (2022)","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"10_CR21","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":"10_CR22","doi-asserted-by":"publisher","unstructured":"Pi, Z., Wan, W., Sun, C., Gao, C., Sang, N., Li, C.: Hierarchical feature embedding for visual tracking. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022, ECCV 2022. LNCS, vol. 13682, pp. 428\u2013445. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_25","DOI":"10.1007\/978-3-031-20047-2_25"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Song, Z., Yu, J., Chen, Y.P.P., Yang, W.: Transformer tracking with cyclic shifting window attention. In: CVPR, pp. 8791\u20138800 (2022)","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Tang, F.: Ranking-based Siamese visual tracking. In: CVPR, pp. 8741\u20138750 (2022)","DOI":"10.1109\/CVPR52688.2022.00854"},{"key":"10_CR26","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, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Towards more flexible and accurate object tracking with natural language: algorithms and benchmark. In: CVPR, pp. 13763\u201313773 (2021)","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Xie, F.: Correlation-aware deep tracking. In: CVPR, pp. 8751\u20138760 (2022)","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, Z., Li, Z., Yuan, Y.: SiamFC++: towards robust and accurate visual tracking with target estimation guidelines. In: AAAI, pp. 12549\u201312556 (2020)","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: ICCV, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Yu, B., Tang, M., Zheng, L., Zhu, G., Wang, J., Feng, H.: High-performance discriminative tracking with transformers. In: ICCV, pp. 9856\u20139865 (2021)","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liu, Y., Wang, X., Li, B., Hu, W.: Learn to match: automatic matching network design for visual tracking. In: ICCV, pp. 13339\u201313348 (2021)","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"10_CR33","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8555-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T07:04:09Z","timestamp":1703660649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8555-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,28]]},"ISBN":["9789819985548","9789819985555"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8555-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,28]]},"assertion":[{"value":"28 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}