{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:19:41Z","timestamp":1783556381711,"version":"3.55.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222664","type":"print"},{"value":"9783032222671","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-22267-1_40","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:09:10Z","timestamp":1783555750000},"page":"514-525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TADT: Task-Aligned Deep Tracking"],"prefix":"10.1007","author":[{"given":"Mengting","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixin","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinrong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Y., Liu, J., Tang, J., Wu, G.: Robust object modeling for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9589\u20139600 (2023)","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R.: Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6668\u20136677 (2020)","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: MixFormer: end-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13608\u201313618 (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ATOM: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Gao, P., Ma, T., Li, H., Lin, Z., Dai, J., Qiao, Y.: MCMAE: masked convolution meets masked autoencoders. In: Advances in Neural Information Processing Systems, vol. 35, pp. 35632\u201335644 (2022)","DOI":"10.52202\/068431-2582"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Hong, L., et\u00a0al.: OneTracker: unifying visual object tracking with foundation models and efficient tuning. arXiv preprint: arXiv:2403.09634 (2024)","DOI":"10.1109\/CVPR52733.2024.01805"},{"issue":"5","key":"40_CR10","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. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR11","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"40_CR14","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representations (2017). https:\/\/api.semanticscholar.org\/CorpusID:53592270"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D.P., Van\u00a0Gool, L.: Learning target candidate association to keep track of what not to track. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13444\u201313454 (2021)","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Proceedings of the European Conference on Computer Vision, pp. 445\u2013461. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"40_CR17","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: Proceedings of the European Conference on Computer Vision, pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"40_CR19","unstructured":"Wang, J., et al.: OmniTracker: unifying object tracking by tracking-with-detection. arXiv preprint: arXiv:2303.12079 (2023)"},{"key":"40_CR20","doi-asserted-by":"publisher","first-page":"103911","DOI":"10.1016\/j.imavis.2020.103911","volume":"97","author":"S Wu","year":"2020","unstructured":"Wu, S., Li, X., Wang, X.: IoU-aware single-stage object detector for accurate localization. Image Vis. Comput. 97, 103911 (2020)","journal-title":"Image Vis. Comput."},{"issue":"9","key":"40_CR21","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834\u20131848 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2014.2388226","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR22","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12549\u201312556 (2020)","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"40_CR24","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1109\/TMM.2021.3074239","volume":"24","author":"K Yang","year":"2021","unstructured":"Yang, K., et al.: SiamCCorners: Siamese corner networks for visual tracking. IEEE Trans. Multimedia 24, 1956\u20131967 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"40_CR25","doi-asserted-by":"publisher","first-page":"106380","DOI":"10.1016\/j.neunet.2024.106380","volume":"176","author":"K Yang","year":"2024","unstructured":"Yang, K., Li, Q., Tian, C., Zhang, H., Shi, A., Li, J.: DeforT: deformable transformer for visual tracking. Neural Netw. 176, 106380 (2024)","journal-title":"Neural Netw."},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: Proceedings of the European Conference on Computer Vision, pp. 341\u2013357. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Yu, Y., Xiong, Y., Huang, W., Scott, M.R.: Deformable Siamese attention networks for visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6728\u20136737 (2020)","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: VarifocalNet: an IoU-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Proceedings of the European Conference on Computer Vision, pp. 771\u2013787. Springer (2020)","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, H., Wang, D., Lu, H.: Representation learning for visual object tracking by masked appearance transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18696\u201318705 (2023)","DOI":"10.1109\/CVPR52729.2023.01793"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22267-1_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:09:13Z","timestamp":1783555753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22267-1_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222664","9783032222671"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22267-1_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}