Discriminative Joint Non-negative Matrix Factorization for Human Action Classification

详细信息    查看全文

• 作者：Abdalrahman Eweiwi (19)
  Muhammad Shahzad Cheema (19)
  Christian Bauckhage (19) (20)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：8142
• 期：1
• 页码：71-80
• 全文大小：948KB
• 参考文献：1. Akata, Z., Thurau, C., Bauckhage, C.: Non-negative matrix factorization in multimodality data for segmentation and label prediction. In: CVWW (2011)
  2. Barker, M., Rayens, W.: Partial least squares for discrimination. J. Chemometrics聽173, 166鈥?73 (2003) CrossRef
  3. Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3d human pose annotations. In: ICCV (2009)
  4. Caicedo, J., BenAbdallah, J., Gonz谩lez, F., Nasraoui, O.: Multimodal representation, indexing, automated annotation and retrieval of image collections via non-negative matrix factorization. Neurocomputing聽76, 50鈥?0 (2012) CrossRef
  5. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
  6. Deltaire, V., Laptev, I., Sivic, J.: Recognizing human actions in still images: A study of bag-of-features and part-based representations. In: BMVC (2010)
  7. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV聽60(2), 91鈥?10 (2004) CrossRef
  8. Ding, C., Li, T., Peng, W.: On the equivalence between non-negative matrix factorization and probabilistic latent semantic indexing. Comput. Stat. Data Anal.聽52, 3913鈥?927 (2008) CrossRef
  9. Dondera, R., Davis, L.: Kernel pls regression for robust monocular pose estimation. In: CVPR-Workshops (2011)
  10. Donner, R., Reiter, M., Langs, G., Peloschek, P., Bischof, H.: Fast active appearance model search using canonical correlation analysis. TPAMI聽28, 1690鈥?694 (2006) CrossRef
  11. Eweiwi, A., Cheema, S., Thurau, C., Bauckhage, C.: Temporal key poses for human action recognition. In: ICCV-Workshops (2011)
  12. Gupta, S., Phung, D., Adams, B., Tran, T., Venkatesh, S.: Nonnegative shared subspace learning and its application to social media retrieval. In: KDD 2010 (2010)
  13. Haj, M., Conza暮ez, J., Davis, L.: On partial least squares in head pose estimation: How to simultaneously deal with misalignment. In: CVPR (2012)
  14. Hotelling, H.: Relations between two sets of variates. Biometrika聽28, 321鈥?77 (1936)
  15. Hskuldsson, A.: Pls regression methods. J. Chemometrics, 211鈥?28 (1988)
  16. Ikizler-Cinbis, N., Cinbis, R., Sclaroff, S.: Learning actions from the web. In: ICCV (2009)
  17. Kim, T., Wong, K.K., Cipolla, R.: Tensor canonical correlation analysis for action classification. In: CVPR (J)
  18. Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. TPAMI聽20, 226鈥?39 (1998) CrossRef
  19. Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
  20. Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature聽401(6755), 788鈥?91 (1999) CrossRef
  21. Liu, J., Wang, C., Gao, J., Han, J.: Multi-view clustering via joint nonnegative matrix factorization. In: SDM (2013)
  22. Maji, S., Bourdev, L., Malik, J.: Action recognition from a distributed representation of pose and appearance. In: CVPR (2011)
  23. Thurau, C., Hlavac, V.: Pose primitive based human action recognition in videos or still images. In: CVPR (2008)
  24. Wang, H., Klaeser, A., Schmid, C., Cheng-Lin, L.: Action recognition by dense trajectories. In: CVPR (2011)
  25. Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR (2010)
  26. Willems, G., Becker, J.H., Tuytelaars, T., Van Gool, L.: Exemplar-based action recognition in video. In: BMVC (2009)
  27. Yang, W., Wang, Y., Mori, G.: Recognizing human actions from still images with latent poses. In: CVPR (2010)
  28. Yao, A., Gall, J., Fanelli, G., Gool, L.V.: Does human action recognition benefit from pose estimation? In: BMVC (2011)
  29. Yao, B., Fei-Fei, L.: Action recognition with exemplar based 2.5D graph matching. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol.聽7575, pp. 173鈥?86. Springer, Heidelberg (2012) CrossRef
  
• 作者单位：Abdalrahman Eweiwi (19)
  Muhammad Shahzad Cheema (19)
  Christian Bauckhage (19) (20)
  
  19. Bonn-Aachen International Center for IT, University of Bonn, Germany
  20. Multimedia Pattern Recognition Group, Fraunhofer IAIS, Germany
  
• ISSN：1611-3349

文摘

This paper describes a supervised classification approach based on non-negative matrix factorization (NMF). Our classification framework builds on the recent expansions of non-negative matrix factorization to multiview learning, where the primary dataset benefits from auxiliary information for obtaining shared and meaningful spaces. For discrimination, we utilize data categories in a supervised manner as an auxiliary source of information in order to learn co-occurrences through a common set of basis vectors. We demonstrate the efficiency of our algorithm in integrating various image modalities for enhancing the overall classification accuracy over different benchmark datasets. Our evaluation considers two challenging image datasets of human action recognition. We show that our algorithm achieves superior results over state-of-the-art in terms of efficiency and overall classification accuracy.