Abstract
In this paper, we develop an interactive Non-negative Matrix Factorization method for representative action video discovery. The original video is first evenly segmented into some short clips and the bag-of-words model is used to describe each clip. Then a temporal consistent Non-negative Matrix Factorization model is used for clustering and action segmentation. Since the clustering and segmentation results may not satisfy the user’s intention, two extra human operations: MERGE and ADD are developed to permit user to improve the results. The newly developed interactive Non-negative Matrix Factorization method can therefore generate personalized results. Experimental results on the public Weizman dataset demonstrate that our approach is able to improve the action discovery and segmentation results.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Shao, L., Jones, S., Li, X.: Efficient Search and Localization of Human Actions in Video Databases. IEEE Trans. Circuits Syst. Video Techn. 24(3), 504–512 (2014)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 556–562 (2001)
Choo, J., Lee, C., Reddy, C.K., Park, H.: Utopian: User-driven topic modeling based on interactive nonnegative matrix factorization. IEEE Trans. on Visualization and Computer Graphics, 1992–2001 (2013)
Cai, D., He, X., Wu, X., Han, J.: Non-negative matrix factorization on manifold. In: Proc. of Eighth IEEE International Conference in Data Mining(ICDM), pp. 63–72 (2008)
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: Proc. of Tenth IEEE International Conference on Computer Vision (ICCV), pp. 1395–1402 (2005)
Hughes, M.C., Sudderth, E.B.: Nonparametric discovery of activity patterns from video collections. In: Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 25–32 (2012)
Wang, M., Ji, D., Tian, Q., Hua, X.S.: Intelligent photo clustering with user interaction and distance metric learning. Pattern Recognition Letters, 462–470 (2012)
Evaluation of clustering. http://nlp.stanford.edu/IR-book/html/htmledition/evaluation-of-clustering-1.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Teng, H., Liu, H., Yu, L., Sun, F. (2015). Representative Video Action Discovery Using Interactive Non-negative Matrix Factorization. In: Hu, X., Xia, Y., Zhang, Y., Zhao, D. (eds) Advances in Neural Networks – ISNN 2015. ISNN 2015. Lecture Notes in Computer Science(), vol 9377. Springer, Cham. https://doi.org/10.1007/978-3-319-25393-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-25393-0_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25392-3
Online ISBN: 978-3-319-25393-0
eBook Packages: Computer ScienceComputer Science (R0)