Abstract
To reduce quantization error, preserve the manifold of local features, distinguish the ambiguous features, and model the spatial configuration of features for Bag-of-Features (BoF) model-based human action recognition, a novel feature coding method called spatially regularized and locality-constrained linear coding (SLLC) is proposed. The spatial regularization and locality constraint are involved in the feature coding phase to model the spatial configuration of features and preserve their nonlinear manifold. The action recognition experimental results on benchmark datasets show that SLLC achieves better performance than the state-of-the-art feature coding methods such as soft vector quantization, sparse coding, and locality-constrained linear coding.
Similar content being viewed by others
References
B. Chakraborty, M. B. Holte, T. B. Moeslund, and J. Gonzàlez: Comput. Vis. Image Understanding 116 (2012) 396.
X. Yan and Y. Luo: Neurocomputing 87 (2012) 51.
H. Wang, M. M. Ullah, A. Klaser, I. Laptev, and C. Schmid: In British Machine Vision Conference, 2009.
I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld: In Computer Vision and Pattern Recognition, 2008, p. 1.
J. C. Niebles, H. Wang, and L. Fei-Fei: Int. J. Comput. Vis. 79 (2008) 299.
H. Wang, A. Klaser, C. Schmid, and C.-L. Liu: In Computer Vision and Pattern Recognition, 2011, p. 3169.
Y. Zhu, X. Zhao, Y. Fu, and Y. Liu: Lect. Notes Comput. Sci. 6493 (2011) 660.
Q. V. Le, W. Y. Zou, S. Y. Yeung, and A. Y. Ng: In Computer Vision and Pattern Recognition, 2011, p. 3361.
J. Wang, Z. Chen, and Y. Wu: In Computer Vision and Pattern Recognition, 2011, p. 3185.
Z. Zhang, C. Wang, B. Xiao, W. Zhou, and S. Liu: IEEE Signal Process. Lett. 19 (2012) 439.
A. Kovashka and K. Grauman: In Computer Vision and Pattern Recognition, 2010, p. 2046.
X. Yan and Y. Luo: Opt. Eng. 50 (2011) 017203.
Y. Zhong and M. Stevens: In Computer Vision and Pattern Recognition, 2010, p. 25.
Z. Zhang, Y. Hu, and S. Chan: In European Conference on Computer Vision, 2008, p. 817.
K. Jia and D.-Y. Yeung: In Computer Vision and Pattern Recognition, 2008, p. 1.
A. A. Chaaraoui, P. Climent-Pérez, and F. Flórez-Revuelta: Pattern Recognit. Lett. 34 (2013) 1799.
J. Wang and Z. Xu: Signal Process. 93 (2013) 2151.
C.-C. Tseng, J.-C. Chen, C.-H. Fang, and J.-J. J. Lien: Pattern Recognition 45 (2012) 3611.
L. Wang, Y. Wang, T. Jiang, D. Zhao, and W. Gao: Pattern Recognition 46 (2013) 1832.
A. M. Hamad and N. Tsumura: Opt. Rev. 19 (2012) 110.
A. M. Hamad and N. Tsumura: Opt. Rev. 19 (2012) 182.
K. Yu, T. Zhang, and Y. Gong: Adv. Neural Inf. Process. Syst. 22 (2009) 2223.
J. Yang, K. Yu, Y. Gong, and T. Huang: In Computer Vision and Pattern Recognition, 2009, p. 1794.
J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong: In Computer Vision and Pattern Recognition, 2010, p. 3360.
J. Sun, X. Wu, S. Yan, L.-F. Cheong, T.-S. Chua, and J. Li: In Computer Vision and Pattern Recognition, 2009, p. 2004.
D. Han, L. Bo, and C. Sminchisescu: In International Conference Computer Vision, 2009, p. 1933.
S. T. Roweis and L. K. Saul: Science 290 (2000) 2323.
R. Poppe: Image Vision Comput. 28 (2010) 976.
J. K. Aggarwal and M. S. Ryoo: ACM Comput. Surv. 43 (2011) 16.
I. Laptev: Int. J. Comput. Vis. 64 (2005) 107.
G. Willems, T. Tuytelaars, and L. V. Gool: In European Conference on Computer Vision, 2008, p. 650.
P. Dollar, V. Rabaud, G. Cottrell, and S. Belongie: Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005, p. 65.
A. Oikonomopoulos, I. Patras, and M. Pantic: IEEE Trans. Syst. Man. Cybern., Part B 36 (2005) 710.
K. Rapantzikos, Y. Avrithis, and S. Kollias: In Computer Vision and Pattern Recognition, 2009, p. 1454.
A. Kläser, M. MarszaŁek, and C. Schmid: In British Machine Vision Conference, 2008.
M.-J. Escobar and P. Kornprobst: Comput. Vis. Image Understanding 116 (2012) 593.
J. C. van Gemert, C. J. Veenman, A. W. M. Smeulders, and J.-M. Geusebroek: IEEE Trans. Pattern Anal. 32 (2010) 1271.
W. E. Vinje and J. L. Gallant: Science 287 (2000) 1273.
B. A. Olshausen and D. J. Field: Vision Res. 37 (1997) 3311.
D. Cai, X. He, and J. Han: In International Conference Computer Vision, 2007, p. 1.
C.-P. Wei, Y.-W. Chao, Y.-R. Yeh, and Y.-C. F. Wang: Pattern Recognition 46 (2013) 1277.
Q. Gu and J. Zhou: In Proceedings of International Conference on Knowledge Discovery and Data Mining, 2009, p. 359.
F. Wu, W. Wang, Y. Yang, Y. Zhuang, and F. Nie: Neurocomputing 73 (2010) 1641.
D. Zhou, O. Bousquet, and T. Lal: Adv. Neural Inf. Process. Syst. 16 (2003) 321.
M. Aharon, M. Elad, and A. Bruckstein: IEEE Trans. Signal Process. 54 (2006) 4311.
M. Marszalek, I. Laptev, and C. Schmid: In Computer Vision and Pattern Recognition, 2009, p. 2929.
H. Lee, A. Battle, R. Raina, and A. Y. Ng: Adv. Neural Inf. Process. Syst. 19 (2007) 801.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, B., Gai, W., Guo, S. et al. Spatially regularized and locality-constrained linear coding for human action recognition. OPT REV 21, 226–236 (2014). https://doi.org/10.1007/s10043-014-0033-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10043-014-0033-x