{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:37:20Z","timestamp":1784212640695,"version":"3.55.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250842","type":"print"},{"value":"9783031250859","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25085-9_26","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"461-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["Efficient Visual Tracking via\u00a0Hierarchical Cross-Attention Transformer"],"prefix":"10.1007","author":[{"given":"Xin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: ECCVW (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"26_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":"26_CR3","unstructured":"Blatter, P., Kanakis, M., Danelljan, M., Van Gool, L.: Efficient visual tracking with exemplar transformers. arXiv preprint arXiv:2112.09686 (2021)"},{"key":"26_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"26_CR5","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":"26_CR6","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":"26_CR7","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: Efficient convolution operators for tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"26_CR8","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":"26_CR9","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":"26_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2020)"},{"key":"26_CR11","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":"26_CR12","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 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"26_CR13","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: ICAIS (2010)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, J., Cui, Y., Wang, Z., Chen, S.: SiamCAR: Siamese fully convolutional classification and regression for visual tracking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR16","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: A large high-diversity benchmark for generic object tracking in the wild. In: TPAMI (2019)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Kiani Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: A benchmark for higher frame rate object tracking. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.128"},{"key":"26_CR18","unstructured":"Kristan, M., et al.: The eighth visual object tracking vot2020 challenge results. In: ECCV (2020)"},{"key":"26_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"26_CR20","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 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"26_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":"26_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":"26_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"26_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"26_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Mueller","year":"2016","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445\u2013461. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27"},{"key":"26_CR26","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":"26_CR27","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":"26_CR28","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: ImageNet Large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"26_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P.H.S., Leibe, B.: Siam R-CNN: Visual tracking by re-detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"26_CR35","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":"26_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.S.: Fast online object tracking and segmentation: A unifying approach. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. In: TPAMI (2015)","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Xie, F., Wang, C., Wang, G., Yang, W., Zeng, W.: Learning tracking representations via dual-branch fully transformer networks. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00303"},{"key":"26_CR39","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: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"26_CR40","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":"26_CR41","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., Lu, H.: Lighttrack: Finding lightweight neural networks for object tracking via one-shot architecture search. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"26_CR42","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":"26_CR43","doi-asserted-by":"crossref","unstructured":"Yu, B., et al.: High-performance discriminative tracking with transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"26_CR44","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":"26_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"26_CR46","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","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25085-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:59:54Z","timestamp":1710269994000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25085-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250842","9783031250859"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25085-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}