{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:09:39Z","timestamp":1793477379468,"version":"4.5.0"},"publisher-location":"Cham","reference-count":46,"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"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_20","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T06:02:55Z","timestamp":1666418575000},"page":"341-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":821,"title":["Joint Feature Learning and\u00a0Relation Modeling for\u00a0Tracking: A One-Stream Framework"],"prefix":"10.1007","author":[{"given":"Botao","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingpeng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"20_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","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":"20_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":"20_CR3","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR, pp. 2544\u20132550 (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: CVPR, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., Yang, X.: High-performance long-term tracking with meta-updater. In: CVPR, pp. 6298\u20136307 (2020)","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: accurate tracking by overlap maximization. In: CVPR, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR, pp. 6638\u20136646 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"20_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 x 16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"2","key":"20_CR11","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","volume":"129","author":"H Fan","year":"2021","unstructured":"Fan, H., et al.: LaSOT: a high-quality large-scale single object tracking benchmark. IJCV 129(2), 439\u2013461 (2021)","journal-title":"IJCV"},{"key":"20_CR12","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":"20_CR13","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":"20_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"20_CR16","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. TPAMI 37(3), 583\u2013596 (2014)","journal-title":"TPAMI"},{"issue":"5","key":"20_CR17","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(5), 1562\u20131577 (2019)","journal-title":"TPAMI"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Jung, I., Son, J., Baek, M., Han, B.: Real-time mdnet. In: ECCV, pp. 83\u201398 (2018)","DOI":"10.1007\/978-3-030-01225-0_6"},{"key":"20_CR19","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, pp. 1125\u20131134 (2017)","DOI":"10.1109\/ICCV.2017.128"},{"key":"20_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS, vol. 25 (2012)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: Detecting objects as paired keypoints. In: ECCV, pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"20_CR22","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":"20_CR23","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, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"20_CR24","unstructured":"Liang, Y., GE, C., Tong, Z., Song, Y., Wang, J., Xie, P.: EViT: expediting vision transformers via token reorganizations. In: ICLR (2022)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Lin, L., Fan, H., Xu, Y., Ling, H.: SwinTrack: a simple and strong baseline for transformer tracking. arXiv preprint arXiv:2112.00995 (2021)","DOI":"10.52202\/068431-1218"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D.P., Van Gool, L.: Learning target candidate association to keep track of what not to track. In: ICCV, pp. 13444\u201313454 (2021)","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: ECCV, pp. 445\u2013461 (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: ECCV, pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR, pp. 4293\u20134302 (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"20_CR33","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NeurIPS, vol. 34 (2021)"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: 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":"20_CR35","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: ImageNet-21k pretraining for the masses. arXiv preprint arXiv:2104.10972 (2021)"},{"key":"20_CR36","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"20_CR37","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347\u201310357 (2021)"},{"key":"20_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P.H., Leibe, B.: Siam R-CNN: visual tracking by re-detection. In: CVPR, pp. 6578\u20136588 (2020)","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"20_CR40","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, pp. 6288\u20136297 (2020)","DOI":"10.1109\/CVPR42600.2020.00632"},{"key":"20_CR41","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":"20_CR42","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":"20_CR43","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":"20_CR44","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J., Mallya, A., Kautz, J., Molchanov, P.: AdaViT: adaptive tokens for efficient vision transformer. arXiv preprint arXiv:2112.07658 (2021)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"20_CR45","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":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: ECCV, pp. 771\u2013787 (2020)","DOI":"10.1007\/978-3-030-58589-1_46"}],"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_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:27:37Z","timestamp":1792628857000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-20047-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_20","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}