Regularized extreme learning machine for multi-view semi-supervised action recognition

Neurocomputing

Volumn 145, Issue , 2014, Pages 250-262

  Iosifidis, Alexandros ^a   Tefas, Anastasios ^a   Pitas, Ioannis ^a  

^a ARISTOTLE UNIVERSITY OF THESSALONIKI   (Greece)

Author keywords

Extreme learning machine; Multi view learning; Semi supervised learning

Indexed keywords

ITERATIVE METHODS; KNOWLEDGE ACQUISITION; SUPERVISED LEARNING;

CLASSIFICATION ALGORITHM; CLASSIFICATION PERFORMANCE; DISCRIMINATION CRITERIA; EXTREME LEARNING MACHINE; MULTI-VIEW LEARNING; SEMI-SUPERVISED LEARNING; SINGLE-HIDDEN LAYER FEEDFORWARD NEURAL NETWORKS; STATE-OF-THE-ART PERFORMANCE;

ALGORITHMS;

ACTION RECOGNITION; ARTICLE; ARTIFICIAL NEURAL NETWORK; BODY MOVEMENT; CLASSIFICATION ALGORITHM; EXTREME LEARNING MACHINE; FUNCTIONAL ASSESSMENT; HUMAN; MACHINE LEARNING; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; PATTERN RECOGNITION; PERCEPTIVE DISCRIMINATION; PRIORITY JOURNAL; PROCESS DEVELOPMENT; PROCESS OPTIMIZATION; STIMULUS RESPONSE; TASK PERFORMANCE;

EID: 84906935799     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2014.05.036     Document Type: Article

References (48)

1. Seo H., Milanfar P. Action recognition from one example. IEEE Trans. Pattern Anal. Mach. Intell. 2011, 33(5):867-882.
2. Laptev I. On space-time interest points. Int. J. Comput. Vis. 2005, 64(2):107-123.
3. S. Sadanand, J. Corso, Action bank: a high-level representation of activity in video, in: IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 1-8.
4. H. Wang, M. Ullah, A. Klaser, I. Laptev, C. Schmid, Evaluation of local spatio-temporal features for action recognition, in: British Machine Vision Conference, vol. 42, no. 1, 2009, pp. 1-11.
5. Gorelick L., Blank M., Shechtman E., Irani M., Basri R. Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell. 2007, 29(12):2247-2253.
6. C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local SVM approach, in: International Conference on Pattern Recognition, 2004, pp. 32-36.
7. N. Gkalelis, H. Kim, A. Hilton, N. Nikolaidis, I. Pitas, The i3DPost multi-view and 3D human action/interaction database, in: Conference on Visual Media Production, 2009, pp. 159-168.
8. Iosifidis A., Tefas A., Pitas I. View-invariant action recognition based on artificial neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2012, 23(3):412-425.
9. Yang S., Wang X., Yang L., Han Y., Jiao L. Semi-supervised action recognition in video via Labeled Kernel Sparse Coding and sparse L1 graph. Pattern Recognit. Lett. 2012, 33:1951-1956.
10. Zhao X., Li X., Pang C., Wang S. Human action recognition based on semi-supervised discriminant analysis with global constraint. Neurocomputing 2013, 105:45-50.
11. Zhang S.X.C., Liu T., Lu H. Boosted multi-class semi-supervised learning for human action recognition. Pattern Recognit. 2011, 44:2334-2342.
12. G. Huang, Q. Zhu, C. Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, in: Proceedings of the IEEE International Joint Conference on Neural Networks, vol. 2, 2004, pp. 985-990.
13. Bartlett P. The sample complexity of pattern classification with neural networks. the size of the weights is more important than the size of the network. IEEE Trans. Inf. Theory 1998, 44(2):525-536.
14. Minhas R., Baradarani A., Seifzadeh S., Jonathan Wu Q. Human action recognition using extreme learning machine based on visual vocabularies. Neurocomputing 2010, 73(10-12):1906-1917.
15. A. Iosifidis, A. Tefas, I. Pitas, Multi-view human action recognition under occlusion based on fuzzy distances and neural networks, in: European Signal Processing Conference.
16. Iosifidis A., Tefas A., Pitas I. Minimum class variance extreme learning machine for human action recognition. IEEE Trans. Circuits Syst. Video Technol. 2013, 23(1):1968-1979.
17. Iosifidis A., Tefas A., Pitas I. Dynamic action recognition based on dynemes and extreme learning machine. Pattern Recognit. Lett. 2013, 34:1890-1898.
18. Yan S., Xu D., Zhang B., Zhang H., Yang Q., Lin S. Graph embedding and extensions. a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell. 2007, 29(1):40-51.
19. Duda R., Hart P., Stork D. Pattern Classification 2000, Wiley-Interscience. 2nd ed.
20. Belkin M., Niyogi P., Sindhwani V. Manifold regularization. a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 2006, 7:2399-2434.
21. Belkin M., Niyogi P. Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv. Neural Inf. Process. Syst. 2001, 14:585-591.
22. Roweis S., Saul L. Nonlinear dimensionality reduction by locally linear embedding. Science 2000, 290(5500):2323-2326.
23. S. Sun, Multi-view Laplacian support vector machines, in: International Conference on Advanced Data Mining and Applications, 2011, pp. 209-222.
24. Kittler J., Hatef M., Duin R., Matas J. On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 1998, 20(3):226-239.
25. Huang G., Zhou H., Ding X., Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 2012, 42(2):513-529.
26. Liu J., Chen Y., Liu M., Zhao Z. SELM: Semi-supervised ELM with application in sparse calibrated location estimation. Neurocomputing 2011, 74:2566-2572.
27. Miche Y., Sorjamaa A., Bas P., Simula O., Jutten C., Lendasse A. OP-ELM. optimally pruned extreme learning machine. IEEE Trans. Neural Netw. 2010, 21(1):158-162.
28. Huang G., Chen L. Convex incremental extreme learning machine. Neurocomputing 2007, 70(16-18):3056-3062.
29. Iosifidis A., Tefas A., Pitas I. Learning sparse representations for view-independent human action recognition based on fuzzy distances. Neurocomputing 2013, 121:334-353.
30. J. Farquhar, D. Hardoon, H. Meng, J. Shawe-Taylor, S. Szedmak, Two view learning: SVM-2K, theory and practice, in: Conference on Neural Information Processing Systems (NIPS).
31. A. Klaser, M. Marszalek, C. Schmid, A spatio-temporal descriptor based on 3d-gradients, in: British Machine Vision Conference, 2009, pp. 995-1004.
32. Savarese S., Delpozo A., Niebles J., Fei-Fei L. Spatial-temporal correlations for unsupervised action classification. IEEE Motion Video Comput. 2008, 1-8.
33. M. Ryoo, M. Shah, J. Aggarwal, Spatio-temporal relationship matdch: video structure comparison for recognition of complex human activities, in: IEEE Computer Vision and Pattern Recognition, 2009, pp. 1593-1600.
34. Liu J., Kuipers B., Savarese S. Recognizing human actions by attributes. IEEE Comput. Vis. Pattern Recognit. 2011, 3337-3344.
35. Laptev I., Marszalek M., Schmind C., Rozenfeld B. Learning realistic human actions from movies. IEEE Comput. Vis. Pattern Recognit. 2008, 1-8.
36. Bregonzio M., Gong S., Ziang T. Recognizing action as clouds of space-time interest points. IEEE Comput. Vis. Pattern Recognit. 2009, 1948-1955.
37. J. Liu, J. Luo, M. Shah, Recognizing realistic actions from videos, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 1996-2003.
38. Q. Le, W. Zou, S. Yeung, A. Ng, Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis, in: IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 3361-3368.
39. J. Liu, M. Shah, Learning human actions via information maximization, in: IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1-8.
40. A. Gilbert, J. Illingworth, R. Bowden, Fast realistic multi-action recognition using mined dense spatio-temporal features, in: International Conference on Computer Vision, 2009, pp. 925-931.
41. A. Kovashka, K. Grauman, Learning a hierarchy of discriminative space-time neighborhood features for human action recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2010, pp. 2046-2053.
42. X. Wu, D. Xu, L. Duan, J. Luo, Action recognition using context and appearance distribution features, in: IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 489-496.
43. Olivia A., Torralba A. Modeling the shape of the scene. a holistic representation of the spatial envelope. Int. J. Comput. Vis. 2001, 42:145-175.
44. M. Holte, T. Moeslund, N. Nikolaidis, I. Pitas, 3D human action recognition for multi-view camera systems, in: IEEE International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 2011, pp. 342-349.
45. Iosifidis A., Tefas A., Nikolaidis N., Pitas I. Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis. Comput. Vis. Image Understand. 2012, 116(3):347-360.
46. A. Iosifidis, A.Tefas, I. Pitas, Neural representation and learning for multi-view human action recognition,in:IEEE International Joint Conferenceon Neural Networks, 2012, pp.2233-2238.
47. Iosifidis A., Tefas A., Pitas I. Multi-view action recognition based on action volumes, fuzzy distances and cluster discriminant analysis. Pattern Recognit. Lett. SignalProcess. 2013, 93:1445-1457.
48. Holte M., Chakraborty B., Gonzalez J., Moeslund T. A local 3D motion descriptor for multi-view human action recognition from 4D spatio-temporal interest points. IEEE J. Sel. Topics Signal Process. 2012, 99:553-565.