When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Volumn 2017-July, Issue , 2017, Pages 1251-1258

  Cavazza, Jacopo ^a,b   Morerio, Pietro ^a   Murino, Vittorio ^a,c  

^a ISTITUTO ITALIANO DI TECNOLOGIA   (Italy)

^b UNIVERSITY OF GENOA   (Italy)

^c UNIVERSITY OF VERONA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION; RECURRENT NEURAL NETWORKS;

ACTION RECOGNITION; CLASSIFICATION NETWORKS; COVARIANCE NETWORKS; EXPERIMENTAL ANALYSIS; FEATURE LEARNING; HOT RESEARCH TOPICS; HUMAN-ACTION RECOGNITION; KERNEL BASED METHODS;

PATTERN RECOGNITION;

EID: 85030258155     PISSN: 21607508     EISSN: 21607516     Source Type: Conference Proceeding    
DOI: 10.1109/CVPRW.2017.165     Document Type: Conference Paper

References (44)

1. R. Anirudh, P. Turaga, J. Su, and A. Srivastava. Elastic functional coding of human actions: From vector-fields to latent variables. In CVPR, 2015.
2. V. Bloom, D. Makris, and V. Argyriou. G3D: A gaming action dataset and real time action recognition evaluation framework. In CVPR, 2012.
3. J. Cavazza, A. Zunino, M. San Biagio, and V. Murino. Kernelized covariance for action recognition. In ICPR, 2016.
4. M. Devanne, H. Wannous, S. Berretti, P. Pala, M. Daoudi, and A. D. Bimbo. 3d human action recognition by shape analysis of motion trajectories on riemannian manifold. In IEEE Transactions on Cybernetics, 2014.
5. Y. Du, W. Wang, and L. Wang. Hierarchical recurrent neural network for skeleton based action recognition. In CVPR, 2015.
6. G. Evangelidis, G. Singh, and R. Horaud. Skeletal quads: Human action recognition using joint quadruples. In ICPR, 2014.
7. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. LIBLINEAR: A library for large linear classification. JMLR, 9:1871-1874, 2008.
8. S. Fothergill, H. M. Mentis, P. Kohli, and S. Nowozin. Instructing people for training gestural interactive systems. In ACM-CHI, 2012.
9. R. Girshick, F. Iandola, T. Darrell, and J. Malik. Deformable part models are convolutional neural networks. In CVPR, 2015.
10. M. Ha Quang, M. San Biagio, L. Bazzani, and V. Murino. Approximate log-Hilbert-Schmidt distances between covariance operators for image classification. In CVPR, 2016.
11. M. Harandi, M. Salzmann, and F. Porikli. Bregman divergences for infinite dimensional covariance matrices. In CVPR, 2014.
12. M. T. Harandi, M. Salzmann, and R. Hartley. From manifold to manifold: geometry-aware dimensionality reduction for SPD matrices. In ECCV, 2014.
13. M. T. Harandi, C. Sanderson, R. Hartley, and B. C. Lovell. Sparse coding and dictionary learning for symmetric positive definite matrices: A kernel approach. In ECCV, 2012.
14. Z. Huang and L. V. Gool. A riemannian network for spd matrix learning. In AAAI, 2017.
15. Z. Huang, C. Wan, T. Probst, and L. V. Gool. Deep learning on lie groups for skeleton-based action recognition. In arXiv:1612. 05877, 2016.
16. M. Hussein, M. Torki, M. Gowayyed, and M. El-Saban. Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. IJCAI, 2013.
17. G. Johansson. Visual perception of biological motion and a model for its analysis. 1973.
18. P. Koniusz, A. Cherian, and F. Porikli. Tensor representation via kernel linearization for action recognition from 3d skeletons. In ECCV, 2016.
19. C. Li, Y. Hou, P. Wang, and W. Li. Joint distance maps based action recognition with convolutional neural network. IEEE Signal Process. Lett., 2017.
20. W. Li, Z. Zhang, and Z. Liu. Action recognition based on a bag of 3d points. In CVPR workshop, 2010.
21. J. Liu, A. Shahroudy, D. Xu, and G. Wang. Spatio-temporal LSTM with trust gates for 3D human action recognition. In ECCV, 2016.
22. L. Lo Presti, M. La Cascia, S. Sclaroff, and O. Camps. Gesture modeling by Hanklet-based hidden Markov model. In ACCV, 2014.
23. J. Mairal, P. Koniusz, Z. Harchaoui, and C. Schmid. Convolutional kernel networks. In NIPS, 2014.
24. P. Morerio, J. Cavazza, R. Volpi, R. Vidal, and V. Murino. Curriculum dropout. In arXiv:1703. 06229, 2017.
25. M. Müller, T. Röder, M. Clausen, B. Eberhardt, B. Krüger, and A. Weber. HDM-05 doc. In Tech. Rep., 2007.
26. S. Nie and Q. Ji. Capturing global and local dynamics for human action recognition. In ICPR, 2014.
27. O. Oreifej and Z. Liu. HON4D: Histogram of oriented 4D normals for activity recognition from depth sequences. In CVPR, 2013.
28. O. Oreifej and Z. Liu. Hon4d: Histogram of oriented normals for activity recognition from depth sequences. In CVPR, 2013.
29. I. Rebai, Y. BenAyed, and W. Mahdi. Deep multilayer multiple kernel learning. NCA, 27 (8), 2016.
30. L. Seidenari, V. Varano, S. Berretti, A. D. Bimbo, and P. Pala. Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses. In CVPRw, 2013.
31. L. Seidenari, V. Varano, S. Berretti, A. D. Bimbo, and P. Pala. Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses. In CVPR workshops, 2013.
32. A. Shahroudy, J. Liu, T.-T. Ng, and G. Wang. NTU RGB+D: A large scale dataset for 3D human activity analysis. In CVPR, 2016.
33. Y. Tang. Deep learning using support vector machines. In ICML workshop, 2013.
34. O. Tuzel, F. Porikli, and P. Meer. Region covariance: A fast descriptor for detection and classification. In ECCV, 2006.
35. R. Vemulapalli, F. Arrate, and R. Chellappa. Human action recognition by representing 3d skeletons as points in a lie group. In CVPR, June 2014.
36. R. Vemulapalli and R. Chellapa. Rolling rotations for recognizing human actions from 3d skeletal data. In CVPR, 2016.
37. L. Wang, J. Zhang, L. Zhou, C. Tang, and W. Li. Beyond covariance: Feature representation with nonlinear kernel matrices. In ICCV, 2015.
38. P. Wang, Z. Li, Y. Hou, and W. Li. Action recognition based on joint trajectory maps using convolutional neural networks. In ACMMM, 2016.
39. R. Wang, H. Guo, L. S. Davis, and Q. Dai. Covariance discriminative learning: A natural and efficient approach to imageset classification. In CVPR, 2013.
40. L. Xia, C.-C. Chen, and J. Aggarwal. View invariant human action recognition using histograms of 3D joints. In CVPR workshops, 2012.
41. L. Xia, C. C. Chen, and J. K. Aggarwal. View invariant human action recognition using histograms of 3d joints. In CVPRw, 2012.
42. X. Yang and Y. Tian. Super normal vector for activity recognition using depth sequences. In CVPR, 2014.
43. X. Zhang, Y. Wang, M. Gou, M. Sznaier, and O. Camps. Efficient temporal sequence comparison and classification using gram matrix embeddings on a riemannian manifold. In CVPR, 2016.
44. Y. Zhu, W. Chen, and G. Guo. Fusing spatiotemporal features and joints for 3d action recognition. In CVPRw, 2013.