Activity Recognition in Still Images with Transductive Non-negative Matrix Factorization

详细信息    查看全文

• 作者：Naiyang Guan (16)
  Dacheng Tao (17)
  Long Lan (16)
  Zhigang Luo (16)
  Xuejun Yang (18)
  
  16. Science and Technology on Parallel and Distributed Processing Laboratory ; College of Computer ; National University of Defense Technology ; Changsha ; People鈥檚 Republic of China
  17. Centre for Quantum Computation and Intelligent Systems and the Faculty of Engineering and Information Technology ; University of Technology ; Sydney ; Australia
  18. State Key Laboratory of High Performance Computing ; National University of Defense Technology ; Changsha ; People鈥檚 Republic of China
  
• 关键词：Still image based action recognition ; Non ; negative matrix factorization ; Transductive learning
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8925
• 期：1
• 页码：802-817
• 全文大小：736 KB
• 参考文献：1. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: International Conference on Computer Vision, vol. 2, pp. 1395鈥?402 (2005)
  2. Laptev, I., Perez, P.: Retrieving actions in movies. In: Proceedings of International Conference on Computer Vision, pp. 1鈥? (2007)
  3. Niebles, JC, Wang, H, Fei-Fei, L (2008) Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. International Journal of Computer Vision 79: pp. 299-318 4" target="_blank" title="It opens in new window">CrossRef
  4. Thurau, C., Hlavac, V.: Pose primitive based human action recognition in videos or still images. In: IEEE Conference on Computer Vision and Pattern Recognition (2008)
  5. Aggarwal, J.K., Xia, L.: Human Activity Recognition from 3DData: A Review. Pattern Recognition Letters (2014)
  6. Waltner, G., Mauthner, T., Bischof, H.: Indoor Activity Detection and Recognition for Sport Games Analysis. arXiv preprint 404.6413" class="a-plus-plus">arXiv:1404.6413 (2014)
  7. Lee, DD, Seung, HS (1999) Learning the Parts of Objects with Non-negative Matrix Factorization. Nature 401: pp. 788-791 44565" target="_blank" title="It opens in new window">CrossRef
  8. Xu, W., Liu, X., Gong, Y.: Document clustering based on nonnegative matrix factorization. In: ACM Special Interest Group on Information Retrieval, pp. 167鈥?73 (2014)
  9. Huang, X, Zheng, X, Yuan, W, Wang, F, Zhu, S (2011) Enhanced Clustering of Biomedical Documents Using Ensemble Nonnegative Matrix Factorization. Information Sciences 181: pp. 2293-2302 CrossRef
  10. Pauca, V, Piper, J, Plemmons, R (2006) Nonnegative Matrix Factorization for Spectral Data Analysis. Linear Algebra and its Applications 416: pp. 29-47 CrossRef
  11. Liu, L, Shao, L, Zhen, X, Li, X (2013) Learning Discriminative Key Poses for Action Recognition. IEEE Transactions on Cybernetics 43: pp. 1860-1870 CrossRef
  12. Zhang, Z, Tao, D (2012) Slow Feature Analysis for Human Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 34: pp. 436-450 CrossRef
  13. Liu, L, Shao, L, Zheng, F, Li, X (2014) Realistic Action Recognition via Sparsely-constructed Gaussian Processes. Pattern Recognition 47: pp. 3819-3827 4.07.006" target="_blank" title="It opens in new window">CrossRef
  14. Hotelling, H (1933) Analysis of a Complex of Statistical Variables into Principal Components. Journal of Educational Psychology 24: pp. 417-441 CrossRef
  15. Fisher, RA (1936) The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7: pp. 179-188 469-1809.1936.tb02137.x" target="_blank" title="It opens in new window">CrossRef
  16. Guan, N., Lan, L., Tao, D., Luo, Z., Yang, X.: Transductive nonnegative matrix factorizationfor semi-supervised high-performance speech separation. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 2553鈥?557 (2014)
  17. Lee, D.D., Seung, H.S.: Algorithms for Non-negative matrix factorization. In: Proceedings of Advances in Neural Information and Processing Systems, pp. 556鈥?62 (2000)
  18. Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 7, pp. 1鈥? (2008)
  19. Ikizler-Cinbis, N., Cinbis, R.G., Sclaroff, S.: Learning actions from the web. In: IEEE International Conference on Computer Vision, pp. 995鈥?002 (2009)
  20. Zheng, Y., Zhang, Y.J., Li, X., Liu, B.D.: Action recognition in still images using a combination of human pose and context information. In: International Conference on Image Processing (2012)
  21. Khan, FS, Anwer, RM, deWeijer, J, Bagdanov, AD, Lopez, AM, Felsberg, M (2013) Coloring Action Recognition in Still Images. International Journal of Computer Vision 105: pp. 205-221 CrossRef
  22. Delaitre, V., Laptev, I., Sivic, J.: Recognizing human actions in still images: astudy of bag-of-features and part-based representations. In: British Machine Vision Conference (2010)
  23. Laptev, I (2005) On Space-time Interest Points. International Journal of Computer Vision 64: pp. 107-123 CrossRef
  24. Guo, G, Lai, A (2014) A Survey on Still Image Based Human Action Recognition. Pattern Recognition 47: pp. 3343-3361 4.04.018" target="_blank" title="It opens in new window">CrossRef
  25. Guan, N, Tao, D, Luo, Z, Yuan, B (2011) Manifold Regularized Discriminative Non-negative Matrix Factorization with Fast Gradient Descent. IEEE Transactions on Image Processing 20: pp. 2030-2048 496" target="_blank" title="It opens in new window">CrossRef
  26. Guan, N, Tao, D, Luo, Z, Yuan, B (2011) Non-negative Patch Alignment Framework. IEEE Transactions on Neural Networks 22: pp. 1218-1230 CrossRef
  27. Li, K, Fu, Y (2014) Prediction of Human Activity by Discovering Temporal Sequence Patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 36: pp. 1644-1657 CrossRef
  28. Kong, Y, Jia, Y, Fu, Y (2014) Interactive Phrases: Semantic Descriptions for Human Interaction Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 36: pp. 1775-1788 4.2303090" target="_blank" title="It opens in new window">CrossRef
  29. Poppe, R (2010) A survey on vision-based human action recognition. Image and Vision Computing 28: pp. 976-990 4" target="_blank" title="It opens in new window">CrossRef
  30. Lambrecht, J., Kleinsorge, M., Rosenstrauch, M., Krger, J.: Spatial Programming for Industrial Robots Through Task Demonstration. International Journal of Advanced Robotic Systems 10(254) (2013)
  31. Danafar, S., Gheissari, N.: Action recognition for surveillance applications using optic flow and SVM. In: Asian Conference on Computer Vision, pp. 457鈥?66 (2007)
  32. Lowe, DG (2004) Distinctive Image Features from Scale-invariant Points. International Journal of Computer Vision 60: pp. 91-110 4.99615.94" target="_blank" title="It opens in new window">CrossRef
  33. Guan, N, Tao, D, Luo, Z, Yuan, B (2012) NeNMF: An Optimal Gradient Method for Non-negative Matrix Factorization. IEEE Transactions on Signal Processing 60: pp. 2882-2898 406" target="_blank" title="It opens in new window">CrossRef
  34. Seijer, J, Schmid, C, Verbeek, JJ, Larlus, D (2009) Learning Color Names for Real-world Applications. IEEE Transactions on Image Processing 18: pp. 1512-1524 CrossRef
  35. Guo, G, Lai, A (2014) A survey on still image based human action recognition. Pattern Recognition 47: pp. 3343-3361 4.04.018" target="_blank" title="It opens in new window">CrossRef
  36. Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L.J., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: International Conference on Computer Vision, Barcelona, Spain, 6鈥?3 November 2011
  
• 作者单位：Computer Vision - ECCV 2014 Workshops
• 丛书名：978-3-319-16177-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Still image based activity recognition is a challenging problem due to changes in appearance of persons, articulation in poses, cluttered backgrounds, and absence of temporal features. In this paper, we proposed a novel method to recognize activities from still images based on transductive non-negative matrix factorization (TNMF). TNMF clusters the visual descriptors of each human action in the training images into fixed number of groups meanwhile learns to represent the visual descriptor of test image on the concatenated bases. Since TNMF learns these bases on both training images and test image simultaneously, it learns a more discriminative representation than standard NMF based methods. We developed a multiplicative update rule to solve TNMF and proved its convergence. Experimental results on both laboratory and real-world datasets demonstrate that TNMF consistently outperforms NMF.