Recurrence Matrices for Human Action Recognition

V. Javier Traver, Pau Agustí, Filiberto Pla

2013

Abstract

One important issue for action characterization consists of properly capturing temporally related information. In this work, recurrence matrices are explored as a way to represent action sequences. A recurrence matrix (RM) encodes all pair-wise comparisons of the frame-level descriptors. By its nature, a recurrence matrix can be regarded as a temporally holistic action representation, but it can hardly be used directly and some descriptor is therefore required to compactly summarize its contents. Two simple RM-level descriptors computed from a given recurrence matrix are proposed. A general procedure to combine a set of RM-level descriptors is presented. This procedure relies on a combination of early and late fusion strategies. Recognition performances indicate the proposed descriptors are competitive provided that enough training examples are available. One important finding is the significant impact on performance of both, which feature subsets are selected, and how they are combined, an issue which is generally overlooked.

References

  1. Aggarwal, J. K. and Ryoo, M. S. (2011). Human activity analysis: A review. ACM Comp. Surv., 43(3).
  2. Ali, S., Basharat, A., and Shah, M. (2007). Chaotic invariants for human action recognition. In ICCV.
  3. BenAbdelkader, C., Cutler, R., and Davis, L. S. (2004). Gait recognition using image self-similarity. EURASIP J. on Applied Signal Processing, 2004(4).
  4. Brendel, W. and Todorovic, S. (2010). Activities as time series of human postures. In ECCV, pages 721-734.
  5. Chang, C.-C. and Lin, C.-J. (2011). LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):27:1-27:27.
  6. Cutler, R. and Davis, L. S. (2000). Robust periodic motion and motion symmetry detection. In CVPR, pages 2615-2622.
  7. Dalal, N. and Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. In CVPR.
  8. Gaidon, A., Harchaoui, Z., and Schmid, C. (2011a). Actom sequence models for efficient action detection. In CVPR, pages 3201-3208.
  9. Gaidon, A., Harchaoui, Z., and Schmid, C. (2011b). A time series kernel for action recognition. In BMVC.
  10. Gorelick, L., Blank, M., Shechtman, E., Irani, M., and Basri, R. (2007). Actions as space-time shapes. PAMI, 29(12):2247-2253.
  11. Junejo, I. N., Dexter, E., Laptev, I., and Pérez, P. (2011). View-independent action recognition from temporal self-similarities. PAMI, 33(1):172-185.
  12. Lan, Z.-z., Bao, L., Yu, S.-I., Liu, W., and Hauptmann, A. G. (2012). Double fusion for multimedia event detection. In Proc. of the 18th Intl. Conf. on Advances in Multimedia Modeling, pages 173-185.
  13. Lucena, M. J., de la Blanca, N. P., and Fuertes, J. M. (2012). Human action recognition based on aggregated local motion estimates. Mach. Vis & Apps. (MVA), 23(1):135-150.
  14. Marwan, N., Romano, M. C., Thiel, M., and Kurthss, J. (2007). Recurrence plots for the analysis of complex systems. Physics Reports, 438(5-6):237-329.
  15. Matikainen, P., Hebert, M., and Sukthankar, R. (2010). Representing pairwise spatial and temporal relations for action recognition. In ECCV, pages 508-521.
  16. Niebles, J. C., Chen, C.-W., and Li, F.-F. (2010). Modeling temporal structure of decomposable motion segments for activity classification. In ECCV, pages 392-405.
  17. Schindler, K. and van Gool, L. (2008). Action snippets: How many frames does human action recognition require? In CVPR.
  18. Serra-Toro, C. and Traver, V. J. (2011). A new pedestrian detection descriptor based on the use of spatial recurrences. In CAIP, pages 97-104.
  19. Tran, D. and Sorokin, A. (2008). Human activity recognition with metric learning. In ECCV, pages 548-561.
Download


Paper Citation


in Harvard Style

Traver V., Agustí P. and Pla F. (2013). Recurrence Matrices for Human Action Recognition . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 271-276. DOI: 10.5220/0004216202710276


in Bibtex Style

@conference{visapp13,
author={V. Javier Traver and Pau Agustí and Filiberto Pla},
title={Recurrence Matrices for Human Action Recognition},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={271-276},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004216202710276},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Recurrence Matrices for Human Action Recognition
SN - 978-989-8565-47-1
AU - Traver V.
AU - Agustí P.
AU - Pla F.
PY - 2013
SP - 271
EP - 276
DO - 10.5220/0004216202710276