Multiple Metric Learning for Graph Based Human Pose Estimation
In this paper, a multiple metric learning scheme for human pose estimation from a single image is proposed. Here, we focused on a big challenge of this problem which is; different 3D poses might correspond to similar inputs. To address this ambiguity, some Euclidean distance based approaches use prior knowledge or pose model that can work properly, provided that the model parameters are being estimated accurately. In the proposed method, the manifold of data is divided into several clusters and then, we learn a new metric for each partition by utilizing not only input features, but also their corresponding poses. The manifold clustering allows the decomposition of multiple manifolds into a set of manifolds that are less complex. Furthermore, the input data could be mapped to a new space where the ambiguity problem is minimized. Our guiding principle for learning the distance metrics is to preserve the manifold structure of the input data. The proposed method employs Tikhonov regularization technique to obtain a smooth estimation of the labels. Experiments on the data set of human pose estimation demonstrate that the proposed multiple metric learning consistently outperforms single-metric learning method across different activities by a wide margin.
KeywordsMultiple metric learning semi-supervised estimation human pose estimation
Unable to display preview. Download preview PDF.
- 3.Pourdamghani, N., Rabiee, H.R., Zolfaghari, M.: Metric learning for graph based semi-supervised human pose estimation. In: 21th IEEE International Conference on Pattern Recognition, pp. 3386–3389. IEEE Press, Tsukuba (2012)Google Scholar
- 4.Jiang, H.: 3D Human Pose Reconstruction Using Millions of Exemplars. In: 20th IEEE International Conference on Pattern Recognition, pp. 1674–1677. IEEE Press, Istanbul (2010)Google Scholar
- 5.Jain, P., Kulis, B., Grauman, K.: Fast image search for learned metrics. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE Press, Anchorage (2008)Google Scholar
- 6.Agarwal, A., Triggs, B.: Monocular Human Motion Capture with a Mixture of Regressors. In: IEEE Conference on Computer Vision and Pattern Recognition, p. 72. IEEE Press, San Diego (2005)Google Scholar
- 8.Xiao, B., Yang, X., Xu, Y., Zha, H.: Learning distance metric for regression by semidefinite programming with application to human age estimation. In: 17th ACM International Conference on Multimedia, pp. 451–460. ACM, Beijing (2009)Google Scholar
- 9.Carnegie Mellon University Motion Capture Database, http://mocap.cs.cmu.edu
- 10.Cui, Z., Li, W., Xu, D., Shan, S., Chen, X.: Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild. In: 26th IEEE Conference on Computer Vision and Pattern Recognition. IEEE Press, Oregon (2013)Google Scholar