{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T09:09:25Z","timestamp":1747386565517,"version":"3.37.3"},"reference-count":94,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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":"crossref","award":["62072042","2020YFC0832502"],"award-info":[{"award-number":["62072042","2020YFC0832502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s00371-023-03013-7","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T14:02:41Z","timestamp":1692626561000},"page":"3103-3117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Structural-appearance information fusion for visual tracking"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9105-6621","authenticated-orcid":false,"given":"Yuping","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zepeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fusheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,21]]},"reference":[{"key":"3013_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103508","volume":"222","author":"F Chen","year":"2022","unstructured":"Chen, F., Wang, X., Zhao, Y., Lv, S., Niu, X.: Visual object tracking: a survey. Comput. Vis. Image Underst. 222, 103508 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"3013_CR2","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s00371-020-01848-y","volume":"37","author":"MY Abbass","year":"2021","unstructured":"Abbass, M.Y., Kwon, K.-C., Kim, N., Abdelwahab, S.A., El-Samie, F.E.A., Khalaf, A.A.: A survey on online learning for visual tracking. Vis. Comput. 37, 993\u20131014 (2021)","journal-title":"Vis. Comput."},{"key":"3013_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, L., Ding, X., Li, W., Leng, J., Lei, B., Yang, W.: A location-aware siamese network for high-speed visual tracking. Appl. Intell., 1\u201317 (2022)","DOI":"10.1007\/s10489-022-03636-8"},{"key":"3013_CR4","doi-asserted-by":"crossref","unstructured":"He, A., Luo, C., Tian, X., Zeng, W.: A twofold siamese network for real-time object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4834\u20134843 (2018)","DOI":"10.1109\/CVPR.2018.00508"},{"key":"3013_CR5","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Wu, B., He, Z., Yang, M.-H.: Target-aware deep tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1369\u20131378 (2019)","DOI":"10.1109\/CVPR.2019.00146"},{"key":"3013_CR6","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: Graph convolutional tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4644\u20134654 (2019)","DOI":"10.1109\/CVPR.2019.00478"},{"key":"3013_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4591\u20134600 (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"3013_CR8","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7952\u20137961 (2019)","DOI":"10.1109\/CVPR.2019.00814"},{"key":"3013_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Q., Feng, W., Zhou, C., Huang, R., Wan, L., Wang, S.: Learning dynamic siamese network for visual object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1763\u20131771 (2017)","DOI":"10.1109\/ICCV.2017.196"},{"key":"3013_CR10","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/s00371-020-01833-5","volume":"37","author":"MY Abbass","year":"2021","unstructured":"Abbass, M.Y., Kwon, K.-C., Kim, N., Abdelwahab, S.A., El-Samie, F.E.A., Khalaf, A.A.: Efficient object tracking using hierarchical convolutional features model and correlation filters. Vis. Comput. 37, 831\u2013842 (2021)","journal-title":"Vis. Comput."},{"key":"3013_CR11","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., Fu, C.: Tctrack: temporal contexts for aerial tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"3013_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: Proceedings of the European Conference on Computer Vision, pp. 254\u2013265 (2014). Springer","DOI":"10.1007\/978-3-319-16181-5_18"},{"key":"3013_CR13","doi-asserted-by":"crossref","unstructured":"Qi, Y., Zhang, S., Qin, L., Yao, H., Huang, Q., Lim, J., Yang, M.-H.: Hedged deep tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4303\u20134311 (2016)","DOI":"10.1109\/CVPR.2016.466"},{"key":"3013_CR14","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":"3013_CR15","doi-asserted-by":"crossref","unstructured":"Choi, J., Chang, H.J., Jeong, J., Demiris, Y., Choi, J.Y.: Visual tracking using attention-modulated disintegration and integration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4321\u20134330 (2016)","DOI":"10.1109\/CVPR.2016.468"},{"key":"3013_CR16","doi-asserted-by":"crossref","unstructured":"Ma, C., Huang, J.-B., Yang, X., Yang, M.-H.: Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3074\u20133082 (2015)","DOI":"10.1109\/ICCV.2015.352"},{"key":"3013_CR17","doi-asserted-by":"crossref","unstructured":"Bhat, G., Johnander, J., Danelljan, M., Khan, F.S., Felsberg, M.: Unveiling the power of deep tracking. In: Proceedings of the European Conference on Computer Vision, pp. 483\u2013498 (2018)","DOI":"10.1007\/978-3-030-01216-8_30"},{"key":"3013_CR18","doi-asserted-by":"crossref","unstructured":"Held, D., Thrun, S., Savarese, S.: Learning to track at 100 fps with deep regression networks. In: Proceedings of the European Conference on Computer Vision, pp. 749\u2013765 (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_45"},{"key":"3013_CR19","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420\u20131429 (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"3013_CR20","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: Proceedings of the European Conference on Computer Vision, pp. 850\u2013865 (2016). Springer","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"3013_CR21","doi-asserted-by":"crossref","unstructured":"Danelljan, M., H\u00e4ger, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310\u20134318 (2015)","DOI":"10.1109\/ICCV.2015.490"},{"key":"3013_CR22","doi-asserted-by":"crossref","unstructured":"Danelljan, M., H\u00e4ger, G., Khan, F.S., Felsberg, M.: Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1430\u20131438 (2016)","DOI":"10.1109\/CVPR.2016.159"},{"key":"3013_CR23","doi-asserted-by":"crossref","unstructured":"Li, F., Tian, C., Zuo, W., Zhang, L., Yang, M.-H.: Learning spatial-temporal regularized correlation filters for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4904\u20134913 (2018)","DOI":"10.1109\/CVPR.2018.00515"},{"key":"3013_CR24","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F.S., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proceedings of the European Conference on Computer Vision, pp. 472\u2013488 (2016). Springer","DOI":"10.1007\/978-3-319-46454-1_29"},{"issue":"5","key":"3013_CR25","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2019.2956703","volume":"43","author":"X Dong","year":"2019","unstructured":"Dong, X., Shen, J., Wang, W., Shao, L., Ling, H., Porikli, F.: Dynamical hyperparameter optimization via deep reinforcement learning in tracking. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1515\u20131529 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3013_CR26","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Shahbaz\u00a0Khan, F., Felsberg, M.: Convolutional features for correlation filter based visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 58\u201366 (2015)","DOI":"10.1109\/ICCVW.2015.84"},{"key":"3013_CR27","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":"3013_CR28","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 Conference on Computer Vision and Pattern Recognition, pp. 4277\u20134286 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"3013_CR29","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 Conference on Computer Vision and Pattern Recognition, pp. 6668\u20136677 (2020)","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"3013_CR30","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 Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"3013_CR31","doi-asserted-by":"crossref","unstructured":"Yan, B., Zhao, H., Wang, D., Lu, H., Yang, X.: \u2019skimming-perusal\u2019 tracking: a framework for real-time and robust long-term tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2385\u20132393 (2019)","DOI":"10.1109\/ICCV.2019.00247"},{"key":"3013_CR32","doi-asserted-by":"crossref","unstructured":"Ma, D., Wu, X.: Capsulerrt: relationships-aware regression tracking via capsules. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10943\u201310952 (2021)","DOI":"10.1109\/CVPR46437.2021.01080"},{"key":"3013_CR33","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Bhat, G., Paul, M., Paudel, D.P., Yu, F., Van\u00a0Gool, L.: Transforming model prediction for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8731\u20138740 (2022)","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"3013_CR34","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 Conference on Computer Vision and Pattern Recognition, pp. 8791\u20138800 (2022)","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"3013_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"3013_CR36","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, Q., Fu, Z., Wang, Y.: Stmtrack: template-free visual tracking with space-time memory networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"3013_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., Yang, M.-H.: Online multi-object tracking with dual matching attention networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 366\u2013382 (2018)","DOI":"10.1007\/978-3-030-01228-1_23"},{"key":"3013_CR38","doi-asserted-by":"crossref","unstructured":"Yin, J., Wang, W., Meng, Q., Yang, R., Shen, J.: A unified object motion and affinity model for online multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6768\u20136777 (2020)","DOI":"10.1109\/CVPR42600.2020.00680"},{"key":"3013_CR39","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Sanet: structure-aware network for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 42\u201349 (2017)","DOI":"10.1109\/CVPRW.2017.275"},{"key":"3013_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 101\u2013117 (2018)","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"3013_CR41","doi-asserted-by":"crossref","unstructured":"Cheng, S., Zhong, B., Li, G., Liu, X., Tang, Z., Li, X., Wang, J.: Learning to filter: siamese relation network for robust tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4419\u20134429 (2021)","DOI":"10.1109\/CVPR46437.2021.00440"},{"key":"3013_CR42","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van\u00a0Gool, L., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6181\u20136190 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"3013_CR43","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 Conference on Computer Vision and Pattern Recognition, pp. 4655\u20134664 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"3013_CR44","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Qi, G., Li, H.: Post: policy-based switch tracking. In: Proceedings of the Association for the Advancement of Artificial Intelligence, vol. 34, pp. 12184\u201312191 (2020)","DOI":"10.1609\/aaai.v34i07.6899"},{"key":"3013_CR45","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 Conference on Computer Vision and Pattern Recognition, pp. 9543\u20139552 (2021)","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"3013_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Weijer, J.V.D., Danelljan, M., Khan, F.S.: Learning the model update for siamese trackers. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4009\u20134018 (2019)","DOI":"10.1109\/ICCV.2019.00411"},{"key":"3013_CR47","doi-asserted-by":"crossref","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., Shah, R.: Signature verification using a \u2019siamese\u2019 time delay neural network. Advances in neural information processing systems 6 (1993)","DOI":"10.1142\/9789812797926_0003"},{"key":"3013_CR48","doi-asserted-by":"crossref","unstructured":"Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: International Workshop on Similarity-Based Pattern Recognition, pp. 84\u201392 (2015). Springer","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"3013_CR49","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735\u20131742 (2006). IEEE"},{"key":"3013_CR50","doi-asserted-by":"crossref","unstructured":"Ni, J., Liu, J., Zhang, C., Ye, D., Ma, Z.: Fine-grained patient similarity measuring using deep metric learning. In: Proceedings of the ACM on Conference on Information and Knowledge Management, pp. 1189\u20131198 (2017)","DOI":"10.1145\/3132847.3133022"},{"key":"3013_CR51","doi-asserted-by":"crossref","unstructured":"Oh\u00a0Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4004\u20134012 (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"3013_CR52","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. Adv.Neural Inf. Proc. Syst.29 (2016)"},{"key":"3013_CR53","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhou, F., Wen, S., Liu, X., Lin, Y.: Deep metric learning with angular loss. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2593\u20132601 (2017)","DOI":"10.1109\/ICCV.2017.283"},{"key":"3013_CR54","unstructured":"Li, Y., Gu, C., Dullien, T., Vinyals, O., Kohli, P.: Graph matching networks for learning the similarity of graph structured objects. In: Proceedings of the International Conference on Machine Learning, pp. 3835\u20133845 (2019). PMLR"},{"key":"3013_CR55","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"3013_CR56","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"issue":"2","key":"3013_CR57","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TETCI.2017.2762739","volume":"2","author":"M Ravanelli","year":"2018","unstructured":"Ravanelli, M., Brakel, P., Omologo, M., Bengio, Y.: Light gated recurrent units for speech recognition. IEEE Trans. Emerg. Top. Comput. Intell. 2(2), 92\u2013102 (2018)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"3013_CR58","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.procs.2018.04.298","volume":"131","author":"G Shen","year":"2018","unstructured":"Shen, G., Tan, Q., Zhang, H., Zeng, P., Xu, J.: Deep learning with gated recurrent unit networks for financial sequence predictions. Proc. Comput. Sci. 131, 895\u2013903 (2018)","journal-title":"Proc. Comput. Sci."},{"key":"3013_CR59","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)"},{"key":"3013_CR60","doi-asserted-by":"crossref","unstructured":"Tan, Q., Ye, M., Yang, B., Liu, S., Ma, A.J., Yip, T.C.-F., Wong, G.L.-H., Yuen, P.: Data-gru: dual-attention time-aware gated recurrent unit for irregular multivariate time series. In: Proceedings of the Association for the Advancement of Artificial Intelligence, vol. 34, pp. 930\u2013937 (2020)","DOI":"10.1609\/aaai.v34i01.5440"},{"key":"3013_CR61","doi-asserted-by":"crossref","unstructured":"Milan, A., Rezatofighi, S.H., Dick, A., Reid, I., Schindler, K.: Online high tracking using recurrent neural networks. In: Proceedings of the Association for the Advancement of Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11194"},{"key":"3013_CR62","doi-asserted-by":"crossref","unstructured":"Cui, Z., Xiao, S., Feng, J., Yan, S.: Recurrently target-attending tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1449\u20131458 (2016)","DOI":"10.1109\/CVPR.2016.161"},{"issue":"3","key":"3013_CR63","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., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"3013_CR64","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"5","key":"3013_CR65","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.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3013_CR66","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., Ling, H.: Lasot: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"3013_CR67","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 (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"3013_CR68","doi-asserted-by":"crossref","unstructured":"Li, S., Yeung, D.-Y.: Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. In: Proceedings of the Association for the Advancement of Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11205"},{"issue":"12","key":"3013_CR69","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":"3013_CR70","doi-asserted-by":"crossref","unstructured":"Xiao, D., Tan, K., Wei, Z., Zhang, G.: Siamese block attention network for online update object tracking. Appl. Intell., 1\u201313 (2022)","DOI":"10.1007\/s10489-022-03619-9"},{"key":"3013_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ma, S., Sclaroff, S.: Meem: robust tracking via multiple experts using entropy minimization. In: Proceedings of the European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"3013_CR72","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.: Staple: Complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401\u20131409 (2016)","DOI":"10.1109\/CVPR.2016.156"},{"key":"3013_CR73","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Shahbaz\u00a0Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310\u20134318 (2015)","DOI":"10.1109\/ICCV.2015.490"},{"key":"3013_CR74","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, B., Ouyang, W., Wang, D., Yang, X., Lu, H.: Gradnet: gradient-guided network for visual object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6161\u20136170 (2019)","DOI":"10.1109\/ICCV.2019.00626"},{"key":"3013_CR75","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R.W., Yang, M.-H.: Vital: visual tracking via adversarial learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8990\u20138999 (2018)","DOI":"10.1109\/CVPR.2018.00937"},{"key":"3013_CR76","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4293\u20134302 (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"3013_CR77","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J., Shao, L., Porikli, F.: Clnet: A compact latent network for fast adjusting siamese trackers. In: European Conference on Computer Vision, pp. 378\u2013395 (2020). Springer","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"3013_CR78","doi-asserted-by":"crossref","unstructured":"Tan, H., Wang, M., Liang, T., Xu, L., Tang, Y., Lan, L., Yang, W.: Self-aware circular response-guided attention for robust siamese tracking. Appl. Intell., 1\u201316 (2022)","DOI":"10.1007\/s10489-022-04314-5"},{"key":"3013_CR79","doi-asserted-by":"crossref","unstructured":"Gupta, D.K., Arya, D., Gavves, E.: Rotation equivariant siamese networks for tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12362\u201312371 (2021)","DOI":"10.1109\/CVPR46437.2021.01218"},{"key":"3013_CR80","doi-asserted-by":"crossref","unstructured":"Wang, G., Luo, C., Xiong, Z., Zeng, W.: Spm-tracker: Series-parallel matching for real-time visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3643\u20133652 (2019)","DOI":"10.1109\/CVPR.2019.00376"},{"key":"3013_CR81","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Van Gool, L., 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":"3013_CR82","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3119\u20133127 (2015)","DOI":"10.1109\/ICCV.2015.357"},{"key":"3013_CR83","doi-asserted-by":"crossref","unstructured":"Chen, B., Wang, D., Li, P., Wang, S., Lu, H.: Real-time \u2019actor-critic\u2019 tracking. In: Proceedings of the European Conference on Computer Vision, pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01234-2_20"},{"key":"3013_CR84","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Parallel tracking and verifying: a framework for real-time and high accuracy visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5487\u20135495 (2017)","DOI":"10.1109\/ICCV.2017.585"},{"key":"3013_CR85","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 International Conference on Computer Vision, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"3013_CR86","doi-asserted-by":"crossref","unstructured":"Li, Y., Fu, C., Ding, F., Huang, Z., Lu, G.: Autotrack: towards high-performance visual tracking for uav with automatic spatio-temporal regularization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11923\u201311932 (2020)","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"3013_CR87","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Tian, Q., Hong, R., Wang, M., Li, H.: Multi-cue correlation filters for robust visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4844\u20134853 (2018)","DOI":"10.1109\/CVPR.2018.00509"},{"issue":"2","key":"3013_CR88","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/TCSVT.2021.3063001","volume":"32","author":"Y Cao","year":"2021","unstructured":"Cao, Y., Ji, H., Zhang, W., Shirani, S.: Feature aggregation networks based on dual attention capsules for visual object tracking. IEEE Trans. Circuits Syst. Video Technol. 32(2), 674\u2013689 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3013_CR89","unstructured":"Fu, C., Jin, J., Ding, F., Li, Y., Lu, G.: Spatial reliability enhanced correlation filter: an efficient approach for real-time uav tracking. IEEE Trans. Multimedia (2021)"},{"key":"3013_CR90","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, Y., Jing, Y., Zhou, P., Zhang, Y.: Fratcf: Feature-residue real-time uav tracking based on automatic spatio-temporal regularization correlation filter. In: 2022 IEEE International Conference on Multimedia and Expo, pp. 1\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859881"},{"key":"3013_CR91","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TMM.2021.3050073","volume":"24","author":"X-F Zhu","year":"2021","unstructured":"Zhu, X.-F., Wu, X.-J., Xu, T., Feng, Z.-H., Kittler, J.: Robust visual object tracking via adaptive attribute-aware discriminative correlation filters. IEEE Trans. Multimedia 24, 301\u2013312 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"3013_CR92","doi-asserted-by":"crossref","unstructured":"Wang, X., Zeng, D., Zhao, Q., Li, S.: Rank-based filter pruning for real-time uav tracking. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 01\u201306 (2022). IEEE","DOI":"10.1109\/ICME52920.2022.9859656"},{"key":"3013_CR93","doi-asserted-by":"crossref","unstructured":"Fu, C., Cao, Z., Li, Y., Ye, J., Feng, C.: Siamese anchor proposal network for high-speed aerial tracking. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 510\u2013516 (2021). IEEE","DOI":"10.1109\/ICRA48506.2021.9560756"},{"key":"3013_CR94","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: Siamapn++: siamese attentional aggregation network for real-time uav tracking. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3086\u20133092 (2021). IEEE","DOI":"10.1109\/IROS51168.2021.9636309"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03013-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03013-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03013-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T09:13:41Z","timestamp":1713518021000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03013-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":94,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["3013"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03013-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2023,8,21]]},"assertion":[{"value":"29 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}