Baseline Results

The following is a set of baseline results from different methods. These results were obtained without using the training set. Only the first frame of the each testing sequence was used to estimate key parameters if needed. Please refer to [1] for details. Please refer to the contest page for related codes.

False-color/Hyperspectral videos Color videos
Tracker AUC DP@20pixels AUC DP@20pixels
MHT [1] 0.5887 0.8876 / /
BACF [2] 0.5440 0.8165 0.5315 0.7917
fDSST [3] 0.4416 0.7047 0.4639 0.7274
KCF [4] 0.4078 0.5834 0.3769 0.6117
VITAL [5] 0.6047 0.9453 0.5759 0.8599
C-COT [6] 0.5572 0.8692 0.6020 0.8971
CFNet [7] 0.5426 0.8756 0.5596 0.8648
References

    [1] F. Xiong, J. Zhou and Y. Qian, "Material Based Object Tracking in Hyperspectral Videos," IEEE Trans. Image Process., vol. 29, no. 1, pp. 3719-3733, 2020. code

    [2] H. K. Galoogahi, A. Fagg, and S. Lucey, “Learning background-aware correlation filters for visual tracking,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 1144–1152. code

    [3] M. Danelljan, G. Hger, F. S. Khan, and M. Felsberg, “Discriminative scale space tracking,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 8, pp. 1561–1575, 2017. code

    [4] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista, “High-speed tracking with kernelized correlation filters,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 3, pp. 583–596, 2015. code

    [5] Y. Song, C. Ma, X. Wu, L. Gong, L. Bao, et al., "VITAL: VIsual Tracking via Adversarial Learning," in Proc. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 8990-8999. code

    [6] M. Danelljan, A. Robinson, F. S. Khan, and M. Felsberg, “Beyond correlation filters: Learning continuous convolution operators for visual tracking,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 472–488. code

    [7] J. Valmadre, L. Bertinetto, J. Henriques, A. Vedaldi, and P. H. S. Torr, “End-to-end representation learning for correlation filter based tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 2805–2813. code