Abstract
Visual tracking is defined as a template-matching task in current Siamese approaches. The tracker needs to locate the target by matching the template with the search area in each frame. Most current Siamese methods either do not use an update strategy or use a linear update method with a fixed learning rate. Neither of the above two strategies allows the target template to dynamically adapt to frequent and dramatic changes in appearance. To solve this problem, we propose a template update model based on the attention mechanism. Our model updates the template in a nonlinear manner. It can fully explore the weight relationship of various features in the template, so that the template can pay more attention to features that are more beneficial to determine the target in different situations. In addition, by adding an adjustment block, the error and invalid information in the old template can be removed before updating. Extensive experiments on several datasets demonstrated the effectiveness of our update model. We used SiamFC++ as our basic tracker and achieved state-of-the-art performance by adding our model. Moreover, our model has lightweight structure, and thus it can be easily applied to most Siamese trackers with minimal computational cost.
F. Jia—Graduate student.
This work is supported by National Natural Science Foundation of China (No. 61802337).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2544–2550. IEEE (2010)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2014)
Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6638–6646 (2017)
Danelljan, M., Robinson, A., Shahbaz Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 472–488. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_29
Lukezic, A., Vojir, T., Cehovin Zajc, L., Matas, J., Kristan, M.: Discriminative correlation filter with channel and spatial reliability. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6309–6318 (2017)
Danelljan, M., Hager, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310–4318 (2015)
Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850–865. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_56
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. 8971–8980 (2018)
Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H.: End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2805–2813 (2017)
Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware Siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103–119. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_7
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. 4282–4291 (2019)
Wang, Q., Teng, Z., Xing, J., Gao, J., Hu, W., Maybank, S.: Learning attentions: residual attentional Siamese network for high performance online visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4854–4863 (2018)
Zhang, L., Gonzalez-Garcia, A., Weijer, J., Danelljan, M., Khan, F.S.: Learning the model update for Siamese trackers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4010–4019 (2019)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Schmidhuber, J., Hochreiter, S.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)
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. 9627–9636 (2019)
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. 34, pp. 12549–12556 (2020)
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. 6269–6277 (2020)
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. 6668–6677 (2020)
Han, G., Du, H., Liu, J., Sun, N., Li, X.: Fully conventional anchor-free Siamese networks for object tracking. IEEE Access 7, 123934–123943 (2019)
Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. arXiv preprint arXiv:2103.15436 (2021)
Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. arXiv preprint arXiv:2103.11681 (2021)
Chu, P., Wang, J., You, Q., Ling, H., Liu, Z.: Spatial-temporal graph transformer for multiple object tracking. arXiv preprint arXiv:2104.00194 (2021)
Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. arXiv preprint arXiv:2103.17154 (2021)
Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 153–169. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_10
Choi, J., Kwon, J., Lee, K.M.: Real-time visual tracking by deep reinforced decision making. Comput. Vis. Image Underst. 171, 10–19 (2018)
Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834–1848 (2015). https://doi.org/10.1109/TPAMI.2014.2388226
Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445–461. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_27
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jia, F., Tang, Z., Gao, Y. (2021). Attention Template Update Model for Siamese Tracker. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13019. Springer, Cham. https://doi.org/10.1007/978-3-030-88004-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-88004-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88003-3
Online ISBN: 978-3-030-88004-0
eBook Packages: Computer ScienceComputer Science (R0)