Abstract
In this paper an unsupervised on-line deep learning algorithm for action recognition in video sequences is proposed. Deep learning models capable of deriving spatio-temporal data have been proposed in the past with remarkable results, yet, they are mostly restricted to building features from a short window length. The model presented here, on the other hand, considers the entire sample sequence and extracts the description in a frame-by-frame manner. Each computational node of the proposed paradigm forms clusters and computes point representatives, respectively. Subsequently, a first-order transition matrix stores and continuously updates the successive transitions among the clusters. Both the spatial and temporal information are concurrently treated by the Viterbi Algorithm, which maximizes a criterion based upon (a) the temporal transitions and (b) the similarity of the respective input sequence with the cluster representatives. The derived Viterbi path is the node’s output, whereas the concatenation of nine vicinal such paths constitute the input to the corresponding upper level node. The engagement of ART and the Viterbi Algorithm in a Deep learning architecture, here, for the first time, leads to a substantially different approach for action recognition. Compared with other deep learning methodologies, in most cases, it is shown to outperform them, in terms of classification accuracy.
Similar content being viewed by others
References
Please provide reference.
Bazzani, L., Freitas, N., Larochelle, H., Murino, V., Ting, J.A.: Learning attentional policies for tracking and recognition in video with deep networks. In: International Conference on Machine Learning, pp. 937–944. ACM (2011).
Bellman, R.: Dynamic Programming. Dover Publications (2003).
Bengio Y (2009) Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1):1–127
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems, pp. 153–160 (2007).
Candès EJ, Romberg JK, Tao T (2006) Stable signal recovery from incomplete and inaccurate measurements. Comm. Pure Appl. Math. 59(8):1207–1223
Carpenter G, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision Graphics and Image Processing 37(1):54–115
Carpenter GA, Gaddam SC (2010) Biased art: A neural architecture that shifts attention toward previously disregarded features following an incorrect prediction. Neural Networks 23(3):435–451
Carpenter GA, Grossberg S (1987) Art 2: Self-organization of stable category recognition codes for analog input patterns. Applied Optics 26:4919–4930
Carpenter GA, Grossberg S (1990) Art 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. Neural Networks 3(2):129–152
Chaquet JM, Carmona EJ, Fernández-Caballero A (2013) A survey of video datasets for human action and activity recognition. Computer Vision and Image Understanding 117(6):633–659
Chen B, Polatkan G, Sapiro G, Blei D, Dunson D, Carin L (2013) Deep learning with hierarchical convolutional factor analysis. Transactions on Pattern Analysis and Machine Intelligence 35(8):1887–1901
Chen SS, Donoho DL, Saunders MA (2001) Atomic decomposition by basis pursuit. SIAM 43(1):129–159
Cheng B, Yang J, Yan S, Fu Y, Huang TS (2010) Learning with l1-graph for image analysis. IEEE Transactions on Image Processing 19(4):858–866
Chopra, S., Balakrishnan, S., Gopalan, R.: Dlid: Deep learning for domain adaptation by interpolating between domains. In: ICML Workshop on Challenges in Representation Learning (2013).
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., de Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems, pp. 2148–2156 (2013).
Diego, F., Hamprecht, F.: Learning multi-level sparse representations. In: Advances in Neural Information Processing Systems, pp. 818–826 (2013).
Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: International Conference on Computer Communications and Networks, pp. 65–72. IEEE (2005).
Donoho DL (2006) For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Communications on pure and applied mathematics 59(6):797–829
Fan J, Xu W, Wu Y, Gong Y (2010) Human tracking using convolutional neural networks. Transactions on Neural Networks 21(10):1610–1623
Fazl-Ersi, E., Elder, J., Tsotsos, J.: Hierarchical classifiers for robust topological robot localization. Journal of Intelligent and Robotic Systems: Theory and Applications pp. 1–17 (2012).
George, D.: How the brain might work: a hierarchical and temporal model for learning and recognition. Ph.D. thesis, Stanford, CA, USA (2008).
Gorelick L, Blank M, Shechtman E, Irani M, Basri R (2007) Actions as space-time shapes. Transactions on Pattern Analysis and Machine Intelligence 29(12):2247–2253
Griffiths TL, Ghahramani Z (2011) The indian buffet process: An introduction and review. Journal of Machine Learning Research 12:1185–1224
Grossberg S (2012) Adaptive resonance theory how a brain learns to consciously attend, learn, and recognize a changing world. Neural Networks 37:1–47
Çaglar Gülçehre, Cho, K., Pascanu, R., Bengio, Y.: Learned-norm pooling for deep neural networks (2013).
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Computation 18(7):1527–1554
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Hoffman, M.D., Blei, D.M., Bach, F.R.: Online learning for latent dirichlet allocation. In: Advances in Neural Information Processing Systems, pp. 856–864 (2010).
Jain, V., Murray, J.F., Roth, F., Turaga, S., Zhigulin, V., Briggman, K.L., Helmstaedter, M.N., Denk, W., Seung, H.S.: Supervised learning of image restoration with convolutional networks. In: International Conference on Computer Vision, pp. 1–8 (2007).
Jain, V., Seung, H.S.: Natural image denoising with convolutional networks. In: Advances in Neural Information Processing Systems, vol. 8, pp. 769–776. Curran Associates, Inc. (2008).
Jhuang, H., Serre, T., Wolf, L., Poggio, T.: A biologically inspired system for action recognition. In: International Conference on Computer Vision, pp. 1–8. IEEE (2007).
Ji S, Xu W, Yang M, Yu K (2013) 3d convolutional neural networks for human action recognition. Pattern Analysis and Machine Intelligence 35(1):221–231
Kavukcuoglu, K., Sermanet, P., Boureau, Y.L., Gregor, K., Mathieu, M., Cun, Y.L.: Learning convolutional feature hierarchies for visual recognition. In: Advances in Neural Information Processing Systems, vol. 1, p. 5 (2010).
Klaser, A., Marszalek, M.: A spatio-temporal descriptor based on 3d-gradients. In: British Machine Vision Conference, pp. 275:1–10 (2008).
Kostavelis I, Gasteratos A (2012) On the optimization of hierarchical temporal memory. Pattern Recognition Letters 33(5):670–676
Laptev I (2005) On space-time interest points. International Journal of Computer Vision 64(2):107–123
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008).
Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order boltzmann machine. In: Advances in Neural Information Processing Systems, pp. 1243–1251 (2010).
Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: Computer Vision and Pattern Recognition, pp. 3361–3368. IEEE (2011).
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: pp. 2278–2324. IEEE (1998).
Lee, H., Pham, P.T., Largman, Y., Ng, A.Y.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in Neural Information Processing Systems, vol. 9, pp. 1096–1104. Curran Associates, Inc. (2009).
Lee TS, Mumford D, Romero R, Lamme VA (1998) The role of the primary visual cortex in higher level vision. Vision research 38(15–16):2429–2454
Lee TSS, Mumford D (2003) Hierarchical bayesian inference in the visual cortex. Journal of the Optical Society of America. A, Optics, image science, and vision 20(7):1434–1448
Levine, S.: Exploring deep and recurrent architectures for optimal control (2013).
Liang, P., Klein, D.: Online em for unsupervised models. In: Proceedings of NAACL, pp. 611–619. Association for Computational Linguistics (2009).
Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.. In: Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008).
Marcellin, M.W., Bilgin, A., Gormish, M.J., Boliek, M.P.: An overview of jpeg-2000. p. 523. IEEE (2000).
Memisevic, R.: On multi-view feature learning. In: International Conference on Machine Learning (2012).
Moghaddam, Weiss, Y., Avidan, S.: Spectral bounds for sparse pca: Exact and greedy algorithms. In: Advances in Neural Information Processing Systems, pp. 915–922. MIT Press (2006).
Moghaddam, B., Weiss, Y., Avidan, S.: Generalized spectral bounds for sparse lda. In: International Conference on Machine learning, pp. 641–648. ACM (2006).
Murray JF, Kreutz-Delgado K (2007) Visual recognition and inference using dynamic overcomplete sparse learning. Neural Computation 19(9):2301–2352
Niebles JC, Wang H, Fei-Fei L (2008) Unsupervised learning of human action categories using spatial-temporal words. International Journal of Computer Vision 79(3):299–318
Norouzi, M., Ranjbar, M., Mori, G.: Stacks of convolutional restricted boltzmann machines for shift-invariant feature learning. In: Computer Vision and Pattern Recognition, pp. 2735–2742. IEEE (2009).
Olshausen, B.A., Fieldt, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by v1. pp. 3311–3325. Elsevier (1997).
Poppe RW (2010) A survey on vision-based human action recognition. Image and Vision Computing 28(6):976–990
Qiao L, Chen S, Tan X (2010) Sparsity preserving projections with applications to face recognition. Pattern Recognition 43(1):331–341
Ramasso E, Panagiotakis C, Pellerin D, Rombaut M (2008) Human action recognition in videos based on the transferable belief model. Pattern analysis and Applications 11(1):1–19
Ranzato, M., Susskind, J., Mnih, V., Hinton, G.: On deep generative models with applications to recognition. In: Computer Vision and Pattern Recognition, pp. 2857–2864. IEEE (2011).
Ranzato, M.A., Huang, F.J., Boureau, Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Computer Vision and Pattern Recognition, vol. 0, pp. 1–8. IEEE, Los Alamitos, CA, USA (2007).
Rodriguez, M.D., Ahmed, J., Shah, M.: Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: Conference on Computer Vision and Pattern Recognition, vol. 0, pp. 1–8. IEEE (2008).
Salakhutdinov R, Tenenbaum JB, Torralba A (2013) Learning with hierarchical-deep models. Transactions on Pattern Analysis and Machine Intelligence 35(8):1958–1971
Saxe, A., McClelland, J., Ganguli, S.: Dynamics of learning in deep linear neural networks. In: Deep Learning Workshop, Advances in Neural Information Processing Systems. Curran Associates, Inc. (2013).
Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local svm approach. In: International Conference on Pattern Recognition, vol. 3, pp. 32–36. IEEE (2004).
Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2007) Robust object recognition with cortex-like mechanisms. Transactions on Pattern Analysis and Machine Intelligence 29(3):411–426
Srivastava, N., Salakhutdinov, R.: Discriminative transfer learning with tree-based priors. In: Advances in Neural Information Processing Systems, pp. 2094–2102. Curran Associates, Inc. (2013).
Tang, Y.: Deep learning using linear support vector machines. In: Workshop on Challenges in Representation Learning, ICML (2013).
Tang, Y., Eliasmith, C.: Deep networks for robust visual recognition. In: International Conference on Machine Learning, pp. 1055–1062 (2010).
Tang, Y., Salakhutdinov, R.: Learning stochastic feedforward neural networks. In: Advances in Neural Information Processing Systems, pp. 530–538. Curran Associates, Inc. (2013).
Taylor, G., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. European Conference on Computer Vision pp. 140–153 (2010).
Theodoridis, S., Koutroumbas, K.: Pattern Recognition, Fourth Edition, 4th edn. Academic Press (2008).
W, L., H, Z., D, T., Y, W., K, L.: Large-scale paralleled sparse principal component analysis. CoRR abs/1312.6182 (2013).
Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C., et al.: Evaluation of local spatio-temporal features for action recognition. In: British Machine Vision Conference, pp. 124.1-124.11 (2009).
Welling, M., Rosen-Zvi, M., Hinton, G.: Exponential family harmoniums with an application to information retrieval. In: Advances in Neural Information Processing Systems, pp. 1481–1488. MIT Press (2005).
Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: European Conference of Computer Vision, pp. 650–663. Springer (2008).
Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. Transactions on Pattern Analysis and Machine Intelligence 31(2):210–227
Yang J, Zhang L, Xu Y, Yang JY (2012) Beyond sparsity: The role of l1-optimizer in pattern classification. Pattern Recognition 45(3):1104–1118
Zeiler, M.D., Krishnan, D., Taylor, G.W., Fergus, R.: Deconvolutional networks. In: Computer Vision and Pattern Recognition, pp. 2528–2535. IEEE (2010).
Zhang, L., Zhou, W.D., Li, F.Z.: Kernel sparse representation-based classifier ensemble for face recognition. Multimedia Tools and Applications pp. 1–15 (2013). DOI 10.1007/s11042-013-1457-1
Zhang, Z., Wang, C., Xiao, B., Zhou, W., Liu, S.: Robust relative attributes for human action recognition. Pattern Analysis and Applications pp. 1–15 (2013).
Zhou G, Sohn K, Lee H (2012) Online incremental feature learning with denoising autoencoders. Journal of Machine Learning Research 22:1453–1461
Zhou Y, Liu K, Carrillo RE, Barner KE, Kiamilev F (2013) Kernel-based sparse representation for gesture recognition. Pattern Recognition 46(12):3208–3222
Zou H, Hastie T, Tibshirani R (2006) Sparse principal component analysis. Journal of Computational and Graphical Statistics 15:265–286
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Charalampous, K., Gasteratos, A. On-line deep learning method for action recognition. Pattern Anal Applic 19, 337–354 (2016). https://doi.org/10.1007/s10044-014-0404-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-014-0404-8