Multi-view Regularized Extreme Learning Machine for Human Action Recognition
In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.
KeywordsExtreme Learning Machine Multi-view Learning Single-hidden Layer Feedforward networks Human Action Recognition
Unable to display preview. Download preview PDF.
- 2.Ji, X., Liu, H.: Advances in View-Invariant Human Motion Analysis: Review. IEEE Transactions on Systems, Man and Cybernetics Part–C 40(1), 13–24 (2010)Google Scholar
- 6.Huang, G., Zhu, Q., Siew, C.: Extreme Learning Machine: A new learning scheme for feedfowrard neural networks. In: IEEE International Joint Conference on Neural Networks (2004)Google Scholar
- 9.Iosifidis, A., Tefas, A., Pitas, I.: Multi-view Human Action Recognition under Occlusion based on Fuzzy Distances and Neural Networks. In: European Signal Processing Conference (2012)Google Scholar
- 13.Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
- 15.Hadfield, S., Bowden, R.: Hollywood 3D: Recognizing Actions in 3D Natural Scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (2013)Google Scholar
- 16.Lanckriet, G.R.G., Cristianini, N., Ghaoui, L.E., Bartlett, P., Jordan, M.I.: Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research 5, 27–72 (2013)Google Scholar
- 17.Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: International Conference on Machine Learning (2004)Google Scholar