{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:00:54Z","timestamp":1780430454935,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819666874","type":"print"},{"value":"9789819666881","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"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\/978-981-96-6688-1_1","type":"book-chapter","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T07:30:12Z","timestamp":1753083012000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Anchor STARK: Query Design for\u00a0Transformer-Based Target Tracking"],"prefix":"10.1007","author":[{"given":"Zhenhai","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lutao","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"1_CR1","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":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"1_CR3","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":"1_CR4","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P.H., Leibe, B.: SIAM R-CNN: visual tracking by re-detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6578\u20136588 (2020)","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"1_CR5","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":"1_CR6","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L.V., Timofte, R.: Probabilistic regression for visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7183\u20137192 (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, H., Piao, Y., Qi, N., Wang, Y.: AtptTrack: asymmetric transformer tracker with prior templates. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2023.3348509"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional SIAMESE networks for object tracking. In: Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8\u201310 and 15\u201316, 2016, Proceedings, Part II 14, pp. 850\u2013865. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1_CR9","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"1_CR10","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6269\u20136277 (2020)","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Guo, D., Shao, Y., Cui, Y., Wang, Z., Zhang, L., Shen, C.: Graph attention tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9543\u20139552 (2021)","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider Siamese networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4591\u20134600 (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"issue":"4","key":"1_CR13","first-page":"5158","volume":"45","author":"Z Chen","year":"2022","unstructured":"Chen, Z., et al.: SiamBAN: target-aware tracking with Siamese box adaptive network. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5158\u20135173 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"1_CR14","doi-asserted-by":"publisher","first-page":"9651","DOI":"10.1007\/s11063-023-11219-y","volume":"55","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Chen, H., Yuan, L., Ren, Y., Tian, H., Wang, X.: SiamMLT: Siamese hybrid multi-layer transformer fusion tracker. Neural Process. Lett. 55(7), 9651\u20139667 (2023)","journal-title":"Neural Process. Lett."},{"key":"1_CR15","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":"1_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR17","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Z., Yuan, L., Ren, Y., Tian, H.: Transformer tracker based on multi-level residual perception structure (2023)","DOI":"10.21203\/rs.3.rs-2799061\/v1"},{"key":"1_CR21","volume":"128","author":"Q Zhu","year":"2024","unstructured":"Zhu, Q., Huang, X., Guan, Q.: TabctNet: target-aware bilateral CNN-transformer network for single object tracking in satellite videos. Int. J. Appl. Earth Obs. Geoinf. 128, 103723 (2024)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR24","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":"1_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: European Conference on Computer Vision, pp. 771\u2013787. Springer (2020)","DOI":"10.1007\/978-3-030-58589-1_46"},{"issue":"1","key":"1_CR26","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/s40537-023-00842-0","volume":"11","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Shafiq, M.O.: Survey of transformers and towards ensemble learning using transformers for natural language processing. J. Big Data 11(1), 25 (2024)","journal-title":"J. Big Data"},{"issue":"9","key":"1_CR27","first-page":"1","volume":"56","author":"J Li","year":"2024","unstructured":"Li, J., Tang, T., Zhao, W.X., Nie, J.Y., Wen, J.R.: Pre-trained language models for text generation: a survey. ACM Comput. Surv. 56(9), 1\u201339 (2024)","journal-title":"ACM Comput. Surv."},{"key":"1_CR28","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":"1_CR29","unstructured":"Zhao, M., Okada, K., Inaba, M.: TRTR: visual tracking with transformer. arXiv preprint arXiv:2105.03817 (2021)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: HIFT: hierarchical feature transformer for aerial tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Mayer, C., et al.: Transforming model prediction for tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8731\u20138740 (2022)","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Song, Z., Yu, J., Chen, Y.P.P., Yang, W.: Transformer tracking with cyclic shifting window attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8791\u20138800 (2022)","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., Ma, C., Wang, X., Yuan, J.: Aiatrack: Attention in attention for transformer visual tracking. In: European Conference on Computer Vision. pp. 146\u2013164. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"1_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"issue":"5","key":"1_CR35","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":"1_CR36","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: European Conference on Computer Vision, pp. 445\u2013461. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"1_CR37","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":"1_CR38","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz\u00a0Khan, F., Felsberg, M.: Eco: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6638\u20136646 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Liang, Y., Li, Q., Long, F.: Global dilated attention and target focusing network for robust tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1549\u20131557 (2023)","DOI":"10.1609\/aaai.v37i2.25241"},{"issue":"12","key":"1_CR40","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. IEEE Trans. Image Process. 24(12), 5630\u20135644 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411\u20132418 (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"1_CR42","unstructured":"Kristan, M., et\u00a0al.: The sixth visual object tracking vot2018 challenge results. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6688-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T19:09:20Z","timestamp":1780427360000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6688-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"ISBN":["9789819666874","9789819666881"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6688-1_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"22 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}