Task Specific Factors for Video Characterization
Factorization methods are used extensively in computer vision for a wide variety of tasks. Existing factorization techniques extract factors that meet requirements such as compact representation, interpretability, efficiency, dimensionality reduction etc. However, when the extracted factors lack interpretability and are large in number, identification of factors that cause the data to exhibit certain properties of interest is useful in solving a variety of problems. Identification of such factors or factor selection has interesting applications in data synthesis and recognition. In this paper simple and efficient methods are proposed, for identification of factors of interest from a pool of factors obtained by decomposing videos represented as tensors into their constituent low rank factors. The method is used to select factors that enable appearance based facial expression transfer and facial expression recognition. Experimental results demonstrate that the factor selection facilitates efficient solutions to these problems with promising results.
KeywordsFacial Expression Singular Value Decomposition Basis Image Expression Recognition Facial Expression Recognition
Unable to display preview. Download preview PDF.
- 1.Tomasi, C., Kanade, T.: Shape and motion without depth. In: Proc. of the Third IEEE International Conf. on Computer Vision, pp. 91–95 (1990)Google Scholar
- 4.Wang, H., Ahuja, N.: Facial expression decomposition. In: Proc. of the Ninth IEEE International Conf. on Computer Vision, pp. 958–965 (2003)Google Scholar
- 5.Hazan, T., Polak, S., Shashua, A.: Sparse image coding using a 3d non-negative tensor factorization. Proc. of the Tenth IEEE International Conf. on Computer Vision, 50–57 (2005)Google Scholar
- 6.Ghahramani, Z., Hinton, G.E.: The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1 (1996)Google Scholar
- 8.Alex, M., Vasilescu, O., Terzopoulos, D.: Multilinear analysis of image ensembles: Tensorfaces. In: Proc. of the Seventh European Conf. on Computer Vision, vol. 1, pp. 447–460 (2002)Google Scholar
- 9.Shashua, A., Levin, A.: Linear image coding for regression and classification using the tensor-rank principle. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 42–49 (2001)Google Scholar
- 10.Shashua, A., Hazan, T.: Non-negative tensor factorization with applications to statistics and computer vision. Proc. of the International Conf. on Machine Learning, 792–799 (2005)Google Scholar
- 11.Platt, J., Cristianini, N., Shawe-Taylor, J.: Large margin dags for multiclass classification. In: Solla, S.A., Leen, T.K., Mueller, K.-R. (eds.) Advances in Neural Information Processing Systems 12, pp. 547–553 (2000)Google Scholar
- 12.Sebe, N., Lew, M.S., Cohen, I., Garg, A., Huang, T.S.: Emotion recognition using a cauchy naive bayes classifier. In: Proc. of the 16 th International Conf. on Pattern Recognition, vol. 1, pp. 17–20 (2002)Google Scholar
- 13.Liu, Z., Shan, Y., Zhang, Z.: Expressive expression mapping with ratio images. In: Proc. of the 28th Annual Conf. on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 271–276 (2001)Google Scholar
- 14.Du, Y., Lin, X.: Mapping emotional status to facial expressions. In: Proc. of the International Conf. on Pattern Recognition, vol. II, pp. 524–527 (2002)Google Scholar
- 15.Ekman, P., Friesen, W.V.: Facial Action Coding System: Investigator’s Guide. Consulting Pshycologists Press, Palo Alto, CA, Palo Alto (1978)Google Scholar