Hessian Regularized Sparse Coding for Human Action Recognition

详细信息    查看全文

• 作者：Weifeng Liu (20)
  Zhen Wang (20)
  Dapeng Tao (21) (22)
  Jun Yu (23)
  
• 关键词：Action recognition ; sparse coding ; Hessian regularization ; manifold learning
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8936
• 期：1
• 页码：502-511
• 全文大小：2,165 KB
• 参考文献：1. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: A large video database for human motion recognition. In: IEEE International Conference on Computer Vision (ICCV), pp. 2556鈥?563 (2011)
  2. Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: A review. ACM Computing Surveys (CSUR)聽43(3), 16 (2011) CrossRef
  3. Ke, Y., Sukthankar, R., Hebert, M.: Spatio-temporal shape and flow correlation for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1鈥? (2007)
  4. Rodriguez, M., Ahmed, J., Shah, M.: Action MACH: A spatio-temporal maximum average correlation height filter for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
  5. Campbell, L.W., Bobick, A.F.: Recognition of human body motion using phase space constraints. In: IEEE International Conference Computer Vision, pp. 624鈥?30 (1995)
  6. Rao, C., Shah, M.: View-invariance in action recognition. In: IEEE Conferences on Computer Vision and Pattern Recognition (CVPR), vol.聽2, p. II-316 (2001)
  7. Sheikh, Y., Sheikh, M., Shah, M.: Exploring the space of a human action. In: IEEE International Conference on Computer Vision, vol. 1, pp. 144鈥?49 (2005)
  8. Chomat, O., Crowley, J.L.: Probabilistic recognition of activity using local appearance. In: IEEE Conference on Computer Vision and Pattern Recognition, vol.聽2 (1999)
  9. Zelnik-Manor, L., Irani, M.: Event-based analysis of video. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol.聽2, p. II-123 (2001)
  10. Laptev, I.: On space-time interest points. International Journal of Computer Vision聽64(2-3), 107鈥?23 (2005) CrossRef
  11. Yilmaz, A., Shah, M.: Actions sketch: A novel action representation. In: IEEE Conference on Computer Vision and Pattern Recognition, vol.聽1, pp. 984鈥?89 (2005)
  12. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: IEEE International Conference on Computer Vision (ICCV), vol.聽2, pp. 1395鈥?402 (2005)
  13. Yu, J., Tao, D., Wang, M., Rui, Y.: Learning to Rank Using User Clicks and Visual Features for Image Retrieval. IEEE Transactions on Cybernetics (2014), 10.1109/TCYB.2014.2336697
  14. Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. International Journal of Computer Vision聽79(3), 299鈥?18 (2008) CrossRef
  15. Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities. In: IEEE International Conference on Computer Vision (ICCV), pp. 1593鈥?600 (2009)
  16. Hong, C., Yu, J., Chen, X.: Image-Based 3D Human Pose Recovery with Locality Sensitive Sparse Retrieval. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2103鈥?108 (2013)
  17. Olshausen, B.A.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature聽381(6583), 607鈥?09 (1996) CrossRef
  18. Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM Journal on Scientific Computing聽20(1), 33鈥?1 (1998) CrossRef
  19. Mallat, S.G., Zhang, Z.: Matching pursuits with time-frequency dictionaries. IEEE Transactions on Signal Processing聽41(12), 3397鈥?415 (1993) CrossRef
  20. Yu, J., Rui, Y., Tao, D.: Click Prediction for Web Image Reranking using Multimodal Sparse Coding. IEEE Transactions on Image Processing聽23(5), 2019鈥?032 (2014) CrossRef
  21. Liu, B.-D., Wang, Y.-X., Zhang, Y.-J., Shen, B.: Learning dictionary on manifolds for image classification. Pattern Recognition聽46(7), 1879鈥?890 (2013) CrossRef
  22. Liu, B.-D., Wang, Y.-X., Shen, B., Zhang, Y.-J., Hebert, M.: Self-explanatory sparse representation for image classification. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol.聽8690, pp. 600鈥?16. Springer, Heidelberg (2014) CrossRef
  23. Yuan, M., Lin, Y.: Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society: Series B (Statistical Methodology)聽68(1), 49鈥?7 (2006) CrossRef
  24. Jenatton, R., Mairal, J., Bach, F.R., Obozinski, G.R.: Proximal methods for sparse hierarchical dictionary learning. In: The 27th International Conference on Machine Learning (ICML), pp. 487鈥?94 (2010)
  25. Jia, Y., Salzmann, M., Darrell, T.: Factorized latent spaces with structured sparsity. In: Advances in Neural Information Processing Systems, pp. 982鈥?90 (2010)
  26. Zheng, M., Bu, J., Chen, C., Wang, C., Zhang, L., Qiu, G., Cai, D.: Graph regularized sparse coding for image representation. IEEE Transactions on Image Processing聽20(5), 1327鈥?336 (2011) CrossRef
  27. Gao, S., Tsang, I.W.-H., Chia, L.-T.: Laplacian sparse coding, hypergraph laplacian sparse coding, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence聽35(1), 92鈥?04 (2013) CrossRef
  28. Zheng, M., Bu, J., Chen, C.: Hessian sparse coding. Neurocomputing聽123, 247鈥?54 (2014) CrossRef
  29. Liu, W., Tao, D., Cheng, J., Tang, Y.: Multiview hessian discriminative sparse coding for image annotation. Computer Vision and Image Understanding聽118, 50鈥?0 (2014) CrossRef
  30. Yu, J., Wang, M., Tao, D.: Semisupervised multiview distance metric learning for cartoon synthesis. IEEE Transactions on Image Processing聽21(11), 4636鈥?648 (2012) CrossRef
  31. Kim, K.I., Steinke, F., Hein, M.: Semi-supervised regression using hessian energy with an application to semi-supervised dimensionality reduction. In: Advances in Neural Information Processing Systems, pp. 979鈥?87 (2009)
  32. Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences聽2(1), 183鈥?02 (2009) CrossRef
  33. Nemirovsky, A.S., Yudin, D.B.: Problem complexity and method efficiency in optimization (1983)
  34. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: A large video database for human motion recognition. In: IEEE International Conference on Computer Vision (ICCV), pp. 2556鈥?563 (2011)
  35. Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. The Journal of Machine Learning Research聽7, 2399鈥?434 (2006)
  36. Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Advances in Neural Information Processing Systems, pp. 801鈥?08 (2006)
  
• 作者单位：Weifeng Liu (20)
  Zhen Wang (20)
  Dapeng Tao (21) (22)
  Jun Yu (23)
  
  20. China University of Petroleum (East China), Qingdao, 266580, China
  21. Shenzhen Institutes of Advanced Technology, Chinese Academy of Science, Shenzhen, China
  22. The Chinese University of Hong Kong, Hong Kong, China
  23. Hangzhou Dianzi University, Hangzhou, 310018, China
  
• ISSN：1611-3349

文摘

With the rapid increase of online videos, recognition and search in videos becomes a new trend in multimedia computing. Action recognition in videos thus draws intensive research concerns recently. Second, sparse representation has become state-of-the-art solution in computer vision because it has several advantages for data representation including easy interpretation, quick indexing and considerable connection with biological vision. One prominent sparse representation algorithm is Laplacian regularized sparse coding (LaplacianSC). However, LaplacianSC biases the results toward a constant and thus results in poor generalization. In this paper, we propose Hessian regularized sparse coding (HessianSC) for action recognition. In contrast to LaplacianSC, HessianSC can well preserve the local geometry and steer the sparse coding varying linearly along the manifold of data distribution. We also present a fast iterative shrinkage-thresholding algorithm (FISTA) for HessianSC. Extensive experiments on human motion database (HMDB51) demonstrate that HessianSC significantly outperforms LaplacianSC and the traditional sparse coding algorithm for action recognition.