{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:13:00Z","timestamp":1774602780338,"version":"3.50.1"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972068"],"award-info":[{"award-number":["61972068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11263-025-02710-1","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:52:03Z","timestamp":1769676723000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Wild Animal Tracking with High-Quality Segment Anything Model and Domain Adaptation"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0097-9541","authenticated-orcid":false,"given":"Ganggang","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0946-0789","authenticated-orcid":false,"given":"Fasheng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7342-7272","authenticated-orcid":false,"given":"Binbin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3341-2197","authenticated-orcid":false,"given":"Hanwei","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7064-903X","authenticated-orcid":false,"given":"Mingshu","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1985-7026","authenticated-orcid":false,"given":"Mengyin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3932-2712","authenticated-orcid":false,"given":"Fuming","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0334-3681","authenticated-orcid":false,"given":"Haojie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"2710_CR1","doi-asserted-by":"publisher","unstructured":"Alawode, B., Dharejo, F. A., Ummar, M., Guo, Y., Mahmood, A., Werghi, N., Khan, F. S., & Javed, S. (2023). Improving underwater visual tracking with a large scale dataset and image enhancement. https:\/\/doi.org\/10.48550\/arXiv.2308.15816. arXiv:2308.15816.","DOI":"10.48550\/arXiv.2308.15816"},{"key":"2710_CR2","doi-asserted-by":"publisher","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., & Torr, P. H. S. (2016). Fully-convolutional siamese networks for object tracking. In G. Hua & H. J\u00e9gou (Eds.), Computer Vision - pp. 850\u2013865. Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"2710_CR3","doi-asserted-by":"publisher","unstructured":"Bideau, P., & Learned-Miller, E. (2016). It\u2019s moving! a probabilistic model for causal motion segmentation in moving camera videos. In Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016, pp. 433\u2013449. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-46484-8_26.","DOI":"10.1007\/978-3-319-46484-8_26"},{"key":"2710_CR4","doi-asserted-by":"publisher","unstructured":"Blatter, P., Kanakis, M., Danelljan, M., & Van Gool, L. (2023). Efficient visual tracking with exemplar transformers. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision pp. 1571\u20131581. https:\/\/doi.org\/10.1109\/WACV56688.2023.00162","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"2710_CR5","doi-asserted-by":"publisher","unstructured":"Borsuk, V., Vei, R., Kupyn, O., Martyniuk, T., Krashenyi, I., & Matas, J. (2022). Fear: Fast, efficient, accurate and robust visual tracker. In Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022, pp. 644\u2013663. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-20047-2_37.","DOI":"10.1007\/978-3-031-20047-2_37"},{"issue":"6","key":"2710_CR6","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.1007\/s11263-023-01762-5","volume":"131","author":"L Cai","year":"2023","unstructured":"Cai, L., McGuire, N. E., Hanlon, R., Mooney, T. A., & Girdhar, Y. (2023). Semi-supervised visual tracking of marine animals using autonomous underwater vehicles. International Journal of Computer Vision,131(6), 1406\u20131427. https:\/\/doi.org\/10.1007\/s11263-023-01762-5","journal-title":"International Journal of Computer Vision"},{"key":"2710_CR7","doi-asserted-by":"publisher","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., & Li, Y. (2021). Hift: Hierarchical feature transformer for aerial tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15457\u201315466. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01517.","DOI":"10.1109\/ICCV48922.2021.01517"},{"issue":"12","key":"2710_CR8","doi-asserted-by":"publisher","first-page":"15834","DOI":"10.1109\/TPAMI.2023.3307174","volume":"45","author":"Z Cao","year":"2023","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., & Fu, C. (2023). Towards real-world visual tracking with temporal contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence,45(12), 15834\u201315849. https:\/\/doi.org\/10.1109\/TPAMI.2023.3307174","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2710_CR9","doi-asserted-by":"publisher","unstructured":"Chen, J., Sun, Q., Zhao, C., Ren, W., & Tang, Y. (2024). Rethinking unsupervised domain adaptation for nighttime tracking. In Luo, B., Cheng, L., Wu, Z.-G., Li, H., Li, C. (Eds.) Neural Information Processing, pp. 391\u2013404. Springer, Singapore. https:\/\/doi.org\/10.1007\/978-981-99-8181-6_30.","DOI":"10.1007\/978-981-99-8181-6_30"},{"key":"2710_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., & Ji, R. (2020). Siamese box adaptive network for visual tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 6668\u20136677. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00670.","DOI":"10.1109\/CVPR42600.2020.00670"},{"issue":"4","key":"2710_CR11","doi-asserted-by":"publisher","first-page":"5158","DOI":"10.1109\/TPAMI.2022.3195759","volume":"45","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R., Tang, Z., & Li, X. (2023). Siamban: Target-aware tracking with siamese box adaptive network. IEEE Transactions on Pattern Analysis and Machine Intelligence,45(4), 5158\u20135173. https:\/\/doi.org\/10.1109\/TPAMI.2022.3195759","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2710_CR12","doi-asserted-by":"publisher","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., & Yang. X. (2020) High-performance long-term tracking with meta-updater. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6298\u20136307. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00633.","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"2710_CR13","doi-asserted-by":"publisher","unstructured":"Dawkins, M., Prior, J., Lewis, B., Faillettaz, R., Banez, T., Salvi, M., Rollo, A., Simon, J., Campbell, M., Lucero, M., Chaudhary, A., Richards, B., & Hoogs, A. (2024). Fishtrack23: An ensemble underwater dataset for multi-object tracking. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision pp. 7167\u20137176. https:\/\/doi.org\/10.1109\/WACV57701.2024.00701.","DOI":"10.1109\/WACV57701.2024.00701"},{"key":"2710_CR14","doi-asserted-by":"publisher","unstructured":"Dong, X., Shen, J., Shao, L., & Porikli, F. (2020). CLNet: A compact latent network for fast adjusting Siamese trackers. In European Conference on Computer Vision. pp. 378\u2013395. https:\/\/doi.org\/10.1007\/978-3-030-58565-5_23.","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"2710_CR15","doi-asserted-by":"publisher","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H.: Lasot,. (2019). 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. https:\/\/doi.org\/10.1109\/CVPR.2019.00552.","DOI":"10.1109\/CVPR.2019.00552"},{"key":"2710_CR16","doi-asserted-by":"publisher","unstructured":"Fu, C., Yao, L., Zuo, H., Zheng, G., & Pan, J. (2024). Sam-da: Uav tracks anything at night with sam-powered domain adaptation. In Proceedings of the IEEE International Conference on Advanced Robotics and Mechatronics, pp. 1\u20131. https:\/\/doi.org\/10.48550\/arXiv.2307.01024.","DOI":"10.48550\/arXiv.2307.01024"},{"key":"2710_CR17","unstructured":"Ganin, Y., & Lempitsky, V. (2015). Unsupervised domain adaptation by backpropagation. In Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 1180\u20131189. https:\/\/proceedings.mlr.press\/v37\/ganin15.html."},{"issue":"9","key":"2710_CR18","doi-asserted-by":"publisher","first-page":"4436","DOI":"10.3390\/s23094436","volume":"23","author":"P Goel","year":"2023","unstructured":"Goel, P., & Ganatra, A. (2023). Unsupervised domain adaptation for image classification and object detection using guided transfer learning approach and js divergence. Sensors,23(9), 4436. https:\/\/doi.org\/10.3390\/s23094436","journal-title":"Sensors"},{"key":"2710_CR19","unstructured":"Gopal, G. Y., & Amer, M. (2023). Mobile vision transformer-based visual object tracking. In Proceedings of the 34th British Machine Vision Conference, pp. 1\u201312. https:\/\/papers.bmvc2023.org\/0800.pdf."},{"key":"2710_CR20","doi-asserted-by":"publisher","unstructured":"Gopal, G. Y., & Amer, M. A. (2024). Separable self and mixed attention transformers for efficient object tracking. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 6708\u20136717. https:\/\/doi.org\/10.1109\/WACV57701.2024.00657.","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"2710_CR21","doi-asserted-by":"publisher","unstructured":"Guo, D., Shao, Y., Cui, Y., Wang, Z., Zhang, L., & Shen, C. (2021). Graph attention tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 9543\u20139552. IEEE. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00942.","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"2710_CR22","doi-asserted-by":"publisher","unstructured":"Guo, D., Wang, J., Cui, Y., Wang, Z., & Chen, S. (2020). 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. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00630.","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"2710_CR23","doi-asserted-by":"publisher","unstructured":"Guo, M., Zhang, Z., Fan, H., Jing, L., Lyu, Y., Li, B., & Hu, W. (2022). Learning target-aware representation for visual tracking via informative interactions. In Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 927\u2013934. IJCAI, Vienna. https:\/\/doi.org\/10.24963\/ijcai.2022\/130.","DOI":"10.24963\/ijcai.2022\/130"},{"key":"2710_CR24","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1109\/TMM.2021.3127357","volume":"25","author":"G Han","year":"2023","unstructured":"Han, G., Su, J., Liu, Y., Zhao, Y., & Kwong, S. (2023). Multi-stage visual tracking with siamese anchor-free proposal network. IEEE Transactions on Multimedia,25, 430\u2013442. https:\/\/doi.org\/10.1109\/TMM.2021.3127357","journal-title":"IEEE Transactions on Multimedia"},{"key":"2710_CR25","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"2710_CR26","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"Huang, L., Zhao, X., & Huang, K. (2021). Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence,43(5), 1562\u20131577. https:\/\/doi.org\/10.1109\/TPAMI.2019.2957464","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2710_CR27","doi-asserted-by":"publisher","unstructured":"Ke, L., Ye, M., Danelljan, M., liu, Y., Tai, Y.-W., Tang, C. -K., & Yu, F. (2023). Segment anything in high quality. In Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, Vol. 36, pp. 29914\u201329934. Curran Associates, Inc., Red Hook, NY, USA.https:\/\/doi.org\/10.48550\/arxiv.2306.01567.","DOI":"10.48550\/arxiv.2306.01567"},{"key":"2710_CR28","doi-asserted-by":"publisher","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., & Lo, W.-Y. (2023). Segment anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2710_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101790","volume":"71","author":"M Klasen","year":"2022","unstructured":"Klasen, M., & Steinhage, V. (2022). Wildlife 3d multi-object tracking. Ecological Informatics,71, Article 101790. https:\/\/doi.org\/10.1016\/j.ecoinf.2022.101790","journal-title":"Ecological Informatics"},{"key":"2710_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2021.101535","volume":"68","author":"M Klasen","year":"2022","unstructured":"Klasen, M., & Steinhage, V. (2022). Improving wildlife tracking using 3d information. Ecological Informatics,68, Article 101535. https:\/\/doi.org\/10.1016\/j.ecoinf.2021.101535","journal-title":"Ecological Informatics"},{"key":"2710_CR31","doi-asserted-by":"publisher","unstructured":"Lamdouar, H., Yang, C., Xie, W., & Zisserman, A. (2021). Betrayed by motion: Camouflaged object discovery via motion segmentation. In Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) Computer Vision \u2013 ACCV 2020, pp. 488\u2013503. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-69532-3_30.","DOI":"10.1007\/978-3-030-69532-3_30"},{"key":"2710_CR32","doi-asserted-by":"publisher","unstructured":"Li, Y., Liu, M., Wu, Y., Wang, X., Yang, X., & Li, S. (2024). Learning adaptive and view-invariant vision transformer for real-time UAV tracking. In Forty-first International Conference on Machine Learning. https:\/\/doi.org\/10.48550\/arXiv.2412.20002.","DOI":"10.48550\/arXiv.2412.20002"},{"key":"2710_CR33","doi-asserted-by":"publisher","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., & Yan, J. (2019). 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. https:\/\/doi.org\/10.1109\/CVPR.2019.00441.","DOI":"10.1109\/CVPR.2019.00441"},{"key":"2710_CR34","doi-asserted-by":"publisher","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., & Hu,. (2018). X.: 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. https:\/\/doi.org\/10.1109\/CVPR.2018.00935.","DOI":"10.1109\/CVPR.2018.00935"},{"key":"2710_CR35","doi-asserted-by":"publisher","unstructured":"Li, S., Yang, X., Wang, X., Zeng, D., Ye, H., & Zhao, Q. (2024). Learning Target-Aware Vision Transformers for Real-Time UAV Tracking. IEEE Transactions on Geoscience and Remote Sensing, 1\u201318. https:\/\/doi.org\/10.1109\/TGRS.2024.3417400.","DOI":"10.1109\/TGRS.2024.3417400"},{"key":"2710_CR36","doi-asserted-by":"publisher","unstructured":"Lin, T. -Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In D., Fleet, T., Pajdla, B., Schiele, T. Tuytelaars, (Eds.) Computer Vision \u2013 ECCV 2014, pp. 740\u2013755. Springer, Cham.https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2710_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109161","volume":"224","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Li, W., Liu, X., Li, Z., & Yue, J. (2024). Deep learning in multiple animal tracking: A survey. Computers and Electronics in Agriculture,224, Article 109161. https:\/\/doi.org\/10.1016\/j.compag.2024.109161","journal-title":"Computers and Electronics in Agriculture"},{"issue":"2","key":"2710_CR38","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/TETCI.2024.3353674","volume":"8","author":"J Liu","year":"2024","unstructured":"Liu, J., Wang, H., Ma, C., Su, Y., & Yang, X. (2024). Siamdmu: Siamese dual mask update network for visual object tracking. IEEE Transactions on Emerging Topics in Computational Intelligence,8(2), 1656\u20131669. https:\/\/doi.org\/10.1109\/TETCI.2024.3353674","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"2710_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111439","volume":"286","author":"Y Li","year":"2024","unstructured":"Li, Y., Wang, B., Wu, X., Liu, Z., & Li, Y. (2024). Lightweight full-convolutional siamese tracker. Knowledge-Based Systems,286, Article 111439. https:\/\/doi.org\/10.1016\/j.knosys.2024.111439","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"2710_CR40","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/s42256-022-00477-5","volume":"4","author":"M Marks","year":"2022","unstructured":"Marks, M., Jin, Q., Sturman, O., von Ziegler, L., Kollmorgen, S., von der Behrens, W., Mante, V., Bohacek, J., & Yanik, M. F. (2022). Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments. Nature Machine Intelligence,4(4), 331\u2013340. https:\/\/doi.org\/10.1038\/s42256-022-00477-5","journal-title":"Nature Machine Intelligence"},{"issue":"3","key":"2710_CR41","first-page":"605","volume":"43","author":"G Ma","year":"2022","unstructured":"Ma, G., Wu, W., Liu, D., Cui, Y., Deng, W., & Jiang, G. (2022). Automatic tracking method of group activities of captive panthera rigris altaica cubs. Chinese Journal of Wildlife,43(3), 605\u2013613.","journal-title":"Chinese Journal of Wildlife"},{"key":"2710_CR42","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1038\/s42256-021-00393-0","volume":"3","author":"Z Miao","year":"2021","unstructured":"Miao, Z., Liu, Z., Gaynor, K. M., Palmer, M. S., Yu, S. X., & Getz, W. M. (2021). Iterative human and automated identification of wildlife images. Nature Machine Intelligence,3, 885\u2013895. https:\/\/doi.org\/10.1038\/s42256-021-00393-0","journal-title":"Nature Machine Intelligence"},{"key":"2710_CR43","doi-asserted-by":"publisher","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., & Ghanem, B. (2018). Trackingnet: A large-scale dataset and benchmark for object tracking in the wild. In Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018, pp. 300\u2013317. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-01246-5_19.","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"2710_CR44","doi-asserted-by":"publisher","unstructured":"Petso, T., Jamisola, R. S., Jr., & Mpoeleng, D. (2022). Review on methods used for wildlife species and individual identification. European Journal of Wildlife Research,68, 3. https:\/\/doi.org\/10.1007\/s10344-021-01549-4.","DOI":"10.1007\/s10344-021-01549-4"},{"key":"2710_CR45","doi-asserted-by":"publisher","unstructured":"Risse, B., Mangan, M., Del Pero, L., & Webb, B. (2017). Visual tracking of small animals in cluttered natural environments using a freely moving camera. In Proccedings of the IEEE International Conference on Computer Vision Workshops. pp. 2840\u20132849. https:\/\/doi.org\/10.1109\/ICCVW.2017.335.","DOI":"10.1109\/ICCVW.2017.335"},{"issue":"3","key":"2710_CR46","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Li, F.-F. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision,115(3), 211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"International Journal of Computer Vision"},{"key":"2710_CR47","doi-asserted-by":"publisher","unstructured":"Sekhavati, A. (2023). Multi-template temporal siamese network for visual object tracking. PhD thesis, Universit\u00e9 d\u2019Ottawa\/University of Ottawa, Ottawa. https:\/\/doi.org\/10.20381\/ruor-28667.","DOI":"10.20381\/ruor-28667"},{"key":"2710_CR48","doi-asserted-by":"publisher","unstructured":"Song, Z., Luo, R., Yu, J., Chen, Y. -P. P., & Yang, W. (2023). Compact transformer tracker with correlative masked modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, pp. 2321\u20132329. https:\/\/doi.org\/10.1609\/aaai.v37i2.25327.","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"2710_CR49","doi-asserted-by":"publisher","unstructured":"Tang, F., & Ling, Q. (2022). Ranking-based siamese visual tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 8741\u20138750. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00854.","DOI":"10.1109\/CVPR52688.2022.00854"},{"key":"2710_CR50","doi-asserted-by":"publisher","unstructured":"Tao, R., Gavves, E., & Smeulders, A. W. (2016). Siamese instance search for tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1420\u20131429. https:\/\/doi.org\/10.1109\/CVPR.2016.158.","DOI":"10.1109\/CVPR.2016.158"},{"issue":"1","key":"2710_CR51","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1038\/s41467-022-27980-y","volume":"13","author":"D Tuia","year":"2022","unstructured":"Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., Kays, R., Klinck, H., Wikelski, M., Couzin, I. D., van Horn, G., Crofoot, M. C., Stewart, C. V., & Berger-Wolf, T. (2022). Perspectives in machine learning for wildlife conservation. Nature Communications,13(1), 792. https:\/\/doi.org\/10.1038\/s41467-022-27980-y","journal-title":"Nature Communications"},{"key":"2710_CR52","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141, & Polosukhin, I. (2017). Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in Neural Information Processing Systems Vol. 30, pp. 6000\u20136010. Red Hook, NY, USA: Curran Associates Inc."},{"issue":"4","key":"2710_CR53","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1007\/s11263-022-01732-3","volume":"131","author":"F Wang","year":"2023","unstructured":"Wang, F., Cao, P., Li, F., Wang, X., He, B., & Sun, F. (2023). Watb: wild animal tracking benchmark. International Journal of Computer Vision,131(4), 899\u2013917. https:\/\/doi.org\/10.1007\/s11263-022-01732-3","journal-title":"International Journal of Computer Vision"},{"key":"2710_CR54","doi-asserted-by":"publisher","first-page":"7933","DOI":"10.1007\/s11063-023-11290-5","volume":"55","author":"F Wang","year":"2023","unstructured":"Wang, F., Cao, P., Wang, X., He, B., & Sun, F. (2023). SiamADT: Siamese Attention and Deformable Features Fusion Network for Visual Object Tracking. Neural Processing Letters,55, 7933\u20137950. https:\/\/doi.org\/10.1007\/s11063-023-11290-5","journal-title":"Neural Processing Letters"},{"key":"2710_CR55","doi-asserted-by":"publisher","unstructured":"Wei, Q., Zeng, B., Liu, J., He, L., & Zeng, G. (2024). LiteTrack: Layer pruning with asynchronous feature extraction for lightweight and efficient visual tracking. In 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 4968\u20134975. https:\/\/doi.org\/10.48550\/arXiv.2309.09249.","DOI":"10.48550\/arXiv.2309.09249"},{"key":"2710_CR56","doi-asserted-by":"publisher","unstructured":"Wu, Y., Wang, X., Yang, X., Liu, M., Zeng, D., Ye, H., & Li, S. (2025). Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking. In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17103\u201317113. https:\/\/doi.org\/10.48550\/arXiv.2504.09228.","DOI":"10.48550\/arXiv.2504.09228"},{"key":"2710_CR57","doi-asserted-by":"publisher","unstructured":"Xing, D., Evangeliou, N., Tsoukalas, A., & Tzes, A. (2022). Siamese transformer pyramid networks for real-time uav tracking. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2139\u20132148. https:\/\/doi.org\/10.1109\/WACV51458.2022.00196.","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"2710_CR58","doi-asserted-by":"publisher","unstructured":"Xu, T., Kang, Z., Zhu, X., & Wu, X. -J. (2024). Learning adaptive spatio-temporal inference transformer for coarse-to-fine animal visual tracking: Algorithm and benchmark. International Journal of Computer Vision, 1\u201315. https:\/\/doi.org\/10.1007\/s11263-024-02008-8.","DOI":"10.1007\/s11263-024-02008-8"},{"key":"2710_CR59","doi-asserted-by":"publisher","unstructured":"Xu, T., Pan, Y., Feng, Z., Zhu, X., Cheng, C., Wu, X. -J., & Kittler, J. (2024). Learning feature restoration transformer for robust dehazing visual object tracking. International Journal of Computer Vision, 1\u201318. https:\/\/doi.org\/10.1007\/s11263-024-02182-9.","DOI":"10.1007\/s11263-024-02182-9"},{"key":"2710_CR60","doi-asserted-by":"publisher","unstructured":"Xue, C., Zhong, B., Liang, Q., Zheng, Y., Li, N., Xue, Y., & Song, S. (2025). Similarity-guided layer-adaptive vision transformer for UAV tracking. In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6730\u20136740. https:\/\/doi.org\/10.48550\/arXiv.2503.06625.","DOI":"10.48550\/arXiv.2503.06625"},{"key":"2710_CR61","doi-asserted-by":"publisher","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., & Lu, H. (2021). Learning spatio-temporal transformer for visual tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10448\u201310457. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01028.","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"2710_CR62","doi-asserted-by":"publisher","unstructured":"Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., & Lu, H. (2021). Lighttrack: Finding lightweight neural networks for object tracking via one-shot architecture search. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15180\u201315189. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01493","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"2710_CR63","doi-asserted-by":"publisher","unstructured":"Yan, B., Zhang, X., Wang, D., Lu, H., & Yang, X. (2021). Alpha-refine: Boosting tracking performance by precise bounding box estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5289\u20135298. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00525","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"2710_CR64","doi-asserted-by":"publisher","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., & Zheng, F. (2023). Track anything: Segment anything meets videos. https:\/\/doi.org\/10.48550\/arXiv.2304.11968. arXiv:2304.11968.","DOI":"10.48550\/arXiv.2304.11968"},{"key":"2710_CR65","doi-asserted-by":"publisher","unstructured":"Yao, L., Fu, C., Li, S., Zheng, G., & Ye, J. (2023). Sgdvit: saliency-guided dynamic vision transformer for uav tracking. In Proccedings of the 2023 IEEE International Conference on Robotics and Automation pp. 3353\u20133359. https:\/\/doi.org\/10.1109\/ICRA48891.2023.10161487.","DOI":"10.1109\/ICRA48891.2023.10161487"},{"key":"2710_CR66","doi-asserted-by":"publisher","unstructured":"Ye, J., Fu, C., Zheng, G., Paudel, D. P., & Chen, G. (2022). Unsupervised domain adaptation for nighttime aerial tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 8896\u20138905. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00869.","DOI":"10.1109\/CVPR52688.2022.00869"},{"key":"2710_CR67","doi-asserted-by":"publisher","unstructured":"Yoo, J., Chung, I., & Kwak, N. (2022). Unsupervised domain adaptation for one-stage object detector using offsets to bounding box. In S., Avidan, G., Brostow, M., Ciss\u00e9, G.M., Farinella, T. Hassner, (Eds.) Computer Vision \u2013 ECCV 2022, (pp. 691\u2013708). Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-19827-4_40.","DOI":"10.1007\/978-3-031-19827-4_40"},{"key":"2710_CR68","doi-asserted-by":"publisher","unstructured":"Yu, Y., Xiong, Y., Huang, W., & Scott, M. R. (2020). Deformable siamese attention networks for visual object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6728\u20136737. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00676","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"2710_CR69","doi-asserted-by":"publisher","unstructured":"Zaveri, R. J., Patel, S., Gu, Y., & Doretto, G. (2025). Improving Accuracy and Generalization for Efficient Visual Tracking. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 9468\u20139478. https:\/\/doi.org\/10.1109\/WACV61041.2025.00917.","DOI":"10.1109\/WACV61041.2025.00917"},{"key":"2710_CR70","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., & Hu, W. (2020). Ocean: Object-aware anchor-free tracking. In Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision \u2013 ECCV 2020, pp. 771\u2013787. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-58589-1_46.","DOI":"10.1007\/978-3-030-58589-1_46"},{"issue":"2","key":"2710_CR71","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1007\/s11263-022-01711-8","volume":"131","author":"L Zhang","year":"2023","unstructured":"Zhang, L., Gao, J., Xiao, Z., & Fan, H. (2023). Animaltrack: A benchmark for multi-animal tracking in the wild. International Journal of Computer Vision,131(2), 496\u2013513. https:\/\/doi.org\/10.1007\/s11263-022-01711-8","journal-title":"International Journal of Computer Vision"},{"key":"2710_CR72","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1007\/s11263-021-01487-3","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, L., Wang, D., Qi, J., & Lu, H. (2021). Learning regression and verification networks for long-term visual tracking. International Journal of Computer Vision,129, 2536\u20132547. https:\/\/doi.org\/10.1007\/s11263-021-01487-3","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2710_CR73","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1049\/ipr2.12629","volume":"17","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Wang, J., Zhang, H., Miao, M., & Wu, D. (2023). Context-aware siamese network for object tracking. IET Image Processing,17(1), 215\u2013226. https:\/\/doi.org\/10.1049\/ipr2.12629","journal-title":"IET Image Processing"},{"issue":"1","key":"2710_CR74","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TPAMI.2022.3153645","volume":"45","author":"H Zhao","year":"2023","unstructured":"Zhao, H., Yan, B., Wang, D., Qian, X., Yang, X., & Lu, H. (2023). Effective local and global search for fast long-term tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,45(1), 460\u2013474. https:\/\/doi.org\/10.1109\/TPAMI.2022.3153645","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2710_CR75","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TPAMI.2022.3153645","volume":"45","author":"H Zhao","year":"2023","unstructured":"Zhao, H., Yan, B., Wang, D., Qian, X., Yang, X., & Lu, H. (2023). Effective local and global search for fast long-term tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,45(1), 460\u2013474. https:\/\/doi.org\/10.1109\/TPAMI.2022.3153645","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2710_CR76","doi-asserted-by":"publisher","unstructured":"Zhu, J., Tang, H., Chen, X., Wang, X., Wang, D., & Lu, H. (2025). Two-stream beats one-stream: asymmetric siamese network for efficient visual tracking. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 10959\u201310967. https:\/\/doi.org\/10.1609\/aaai.v39i10.33191.","DOI":"10.1609\/aaai.v39i10.33191"},{"key":"2710_CR77","doi-asserted-by":"publisher","unstructured":"Zhu, H., Yin, H., Xia, D., Wang, D.-H., Liu, X., & Zhu, S. (2022). Joint pixel-level and feature-level unsupervised domain adaptation for surveillance face recognition. In S. Yu, Z. Zhang, P. C. Yuen, J. Han, T. Tan, Y. Guo, J. Lai, & J. Zhang (Eds.), Pattern Recognition and Computer Vision pp. 461\u2013472. Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-031-18913-5_36","DOI":"10.1007\/978-3-031-18913-5_36"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02710-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02710-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02710-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:38:59Z","timestamp":1774600739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02710-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":77,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["2710"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02710-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"10 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"90"}}