cvpr cvpr2013 cvpr2013-324 cvpr2013-324-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton van_den_Hengel
Abstract: Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking. Structured learning has shown good results when applied to tracking whole targets, but applying this approach to a part-based target model is complicated by the need to model the relationships between parts, and to avoid lengthy initialisation processes. We thus propose a method which models the unknown parts using latent variables. In doing so we extend the online algorithm pegasos to the structured prediction case (i.e., predicting the location of the bounding boxes) with latent part variables. To better estimate the parts, and to avoid over-fitting caused by the extra model complexity/capacity introduced by theparts, wepropose a two-stage trainingprocess, based on the primal rather than the dual form. We then show that the method outperforms the state-of-the-art (linear and non-linear kernel) trackers.
[1] A. Adam, E. Rivlin, and I. Shimshoni. Robust fragments-based tracking using the integral histogram. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., volume 1, pages 798 805, 2006.
[2] Y. Amit and A. Trouv ´e. POP: Patchwork of Parts Models for Object Recognition. Int. J. Comp. Vis., 75(2):267–282, 2007.
[3] S. Avidan. Support vector tracking. IEEE Trans. Pattern Anal. & Mach. Intelli., 26(8): 1064 –1072, 2004.
[4] B. Babenko, M.-H. Yang, and S. Belongie. Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. & Mach. Intelli., 33(8): 1619 –1632, 2011.
[5] M. B. Blaschko and C. H. Lampert. Learning to localize objects with structured output regression. In Proc. Eur. Conf. Comp. Vis., volume 5302, pages 2–15, 2008.
[6] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. Int. J. Comp. Vis., 88(2):303– 338, June 2010.
[7] P. F. Felzenszwalb, R. B. Girshick, D. A. McAllester, and D. Ramanan. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell., 32(9):1627–1645, 2010.
[8] H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via on-line boosting. In Proc. British Mach. Vis. Conf., volume 1, pages 47–56, 2006.
[9] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised on-line boosting for robust tracking. In Proc. Eur. Conf. Comp. Vis., pages 234–247, 2008.
[10] S. Hare, A. Saffari, and P. Torr. Struck: Structured output tracking with kernels. In Proc. Int. Conf. Comp. Vis., pages 263–270, 201 1.
[11] G. Hua and Y. Wu. Measurement integration under inconsistency for robust tracking. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., 2006.
[12] J. Kwon and K. M. Lee. Tracking of a non-rigid object via patch-based dynamic appearance modeling and adaptive basin hopping monte carlo sampling. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., 2009.
[13] J. Kwon and K. M. Lee. Visual tracking decomposition. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., pages 1269–1276, 2010.
[14] H. Li, C. Shen, and Q. Shi. Real-time visual tracking using compressive sensing. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., pages 1305 –13 12, 2011.
[15] Z. Lin, G. Hua, and L. S. Davis. Multiple instance feature for robust part-based object detection. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., 2009.
[16] X. Mei and H. Ling. Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. Pattern Anal. & Mach. Intelli., 33:2259 –2272, 2011.
[17] M. Pedersoli, A. Vedaldi, and J. Gonzalez. A coarse-to-fine approach for fast deformable object detection. In Proc. IEEE Conf. Comp. Vis. & Pattern –
[18]
[19]
[20]
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28]
[29] Recogn., 2011. D. A. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental learning for robust visual tracking. Int. J. Comp. Vis., 77: 125–141, 2008. P. Schnitzspan, S. Roth, and B. Schiele. Automatic discovery of meaningful object parts with latent crfs. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., pages 121–128, 2010. S. M. N. Shahed, J. Ho, and M.-H. Yang. Visual tracking with histograms and articulating blocks. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., 2008. S. Shalev-Shwartz, Y. Singer, and N. Srebro. Pegasos: Primal estimated subgradient solver for SVM. In Proc. Int. Conf. Mach. Learn., 2007. I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun. Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res., 6: 1453–1484, 2005. A. Vedaldi and A. Zisserman. Structured output regression for detection with partial truncation. In Proc. Adv. Neural Info. Process. Syst., 2009. P. A. Viola and M. J. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., pages 511–518, 2001. X. Wang, G. Hua, and T. X. Han. Discriminative tracking by metric learning. In Proc. Eur. Conf. Comp. Vis., pages 200–214, 2010. R. Yao, Q. Shi, C. Shen, Y. Zhang, and A. van den Hengel. Robust tracking with weighted online structured learning. In Proc. Eur. Conf. Comp. Vis., 2012. C. N. J. Yu and T. Joachims. Learning structural svms with latent variables. In Proc. Int. Conf. Mach. Learn., pages 1169–1 176, 2009. K. Zhang, L. Zhang, and M.-H. Yang. Real-time compressive tracking. In Proc. Eur. Conf. Comp. Vis., 2012. L. Zhu, Y. Chen, A. L. Yuille, and W. T. Freeman. Latent hierarchical structural learning for object detection. In Proc. IEEE Conf. Comp. Vis. & Pattern Recogn., pages 1062–1069, 2010. 222333667088