Estimating Human Actions Affinities Across Views

Nicoletta Noceti, Alessandra Sciutti, Francesco Rea, Francesca Odone, Giulio Sandini

2015

Abstract

This paper deals with the problem of estimating the affinity level between different types of human actions observed from different viewpoints. We analyse simple repetitive upper body human actions with the goal of producing a view-invariant model from simple motion cues, that have been inspired by studies on the human perception. We adopt a simple descriptor that summarizes the evolution of spatio-temporal curvature of the trajectories, which we use for evaluating the similarity between actions pair on a multi-level matching. We experimentally verified the presence of semantic connections between actions across views, inferring a relations graph that shows such affinities.

References

  1. Aggarwal, J. and Ryoo, M. (2011). Human activity analysis: A review. ACM Computing Surveys.
  2. Camaioni, L. (2004). The role of declarative pointing in developing a theory of mind. Infancy, 5:291-308.
  3. Fanello, S. R., Gori, I., Metta, G., and Odone, F. (2013). Keep it simple and sparse: Real-time action recognition. J. Mach. Learn. Res., 14(1):2617-2640.
  4. Farah, M. J., Wilson, K. D., Drain, H. M., and Tanaka, J. R. (1995). The inverted face inversion effect in prosopagnosia: Evidence for mandatory, face-specific perceptual mechanisms. Vision Research, 35(14):2089 - 2093.
  5. Gong, D. and Medioni, G. (2011). Dynamic manifold warping for view invariant action recognition. ICCV, pages 571-578.
  6. Goren, C. C., Sarty, M., and Wu, P. Y. K. (1975). Visual following and pattern discrimination of face-like stimuli by newborn infants. Pediatrics, 56(4):544-549.
  7. Huang, C.-H., Yeh, Y.-R., and Wang, Y.-C. (2012a). Recognizing actions across cameras by exploring the correlated subspace. In ECCV, volume 7583 of Lecture Notes in Computer Science, pages 342-351.
  8. Huang, K., Zhang, Y., and Tan, T. (2012b). A discriminative model of motion and cross ratio for view-invariant action recognition. IEEE Transactions on Image Processing, 21(4):2187-2197.
  9. Junejo, I. N., Dexter, E., Laptev, I., and Prez, P. (2011). View-independent action recognition from temporal self-similarities. IEEE Trans. Pattern Anal. Mach. Intell., 33(1):172-185.
  10. Kanakogi, Y. and Itakura, S. (2011). Developmental correspondence between action prediction and motor ability in early infancy. Nat.Commun., 2:341-.
  11. Kuhlmeier, V. A., Troje, N. F., and Lee, V. (2010). Young infants detect the direction of biological motion in point-light displays. Infancy, 15(1):83-93.
  12. Lewandowski, M., Makris, D., and Nebel, J.-C. (2010). View and style-independent action manifolds for human activity recognition. In ECCV, volume 6316 of Lecture Notes in Computer Science, pages 547-560.
  13. Li, B., Camps, O. I., and Sznaier, M. (2012). Cross-view activity recognition using hankelets. In CVPR, pages 1362-1369.
  14. Li, R. and Zickler, T. (2012). Discriminative virtual views for cross-view action recognition. In CVPR, pages 2855-2862.
  15. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. IJCV, 60:91-110.
  16. Mahbub, U., Imtiaz, H., Roy, T., Rahman, S., and Ahad, A. (2011). Action recognition from one example. Pattern Recognition Letters.
  17. Malgireddy, M. R., Inwogu, I., and Govindaraju, V. (2012). A temporal bayesian model for classifying, detecting and localizing activities in video sequences. In CVPRW.
  18. Metta, G., Sandini, G., Vernon, D., Natale, L., and Nori, F. (2008). The icub humanoid robot: An open platform for research in embodied cognition. In Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, PerMIS 7808, pages 50-56.
  19. Noceti, N. and Odone, F. (2012). Learning common behaviors from large sets of unlabeled temporal series. Image and Vision Computing, 30(11):875 - 895.
  20. Perona, P. and Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. PAMI, 12(7):629- 639.
  21. Rao, C., Yilmaz, A., and Shah, M. (2002). View-invariant representation and recognition of actions. IJCV, 50(2):203-226.
  22. Sciutti, A., Noceti, N., Rea, F., Odone, F., Verri, A., and Sandini, G. (2014). The informative content of optical flow features of biological motion. In ECVP.
  23. Shi, J. and Tomasi, C. (1994). Good features to track. In CVPR, pages 593 - 600.
  24. Simion, F., Regolin, L., and Bulf, H. (2008). A predisposition for biological motion in the newborn baby. Proceedings of the National Academy of Sciences, 105(2):809-813.
  25. Troje, N. F. and Westhoff, C. (2006). The inversion effect in biological motion perception: Evidence for a life detector? Current Biology, 16(8):821 - 824.
  26. Wang, X., Ma, X., and Grimson, W. (2009). Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models. IEEE transactions on pattern analysis and machine intelligence, 31(3):539-555.
  27. Welch, G. and Bishop, G. (1995). An introduction to the kalman filter. Technical report.
  28. Wu, X. and Jia, Y. (2012). View-invariant action recognition using latent kernelized structural svm. In ECCV 2012, volume 7576 of Lecture Notes in Computer Science, pages 411-424.
  29. Zheng, J. and Jiang, Z. (2013). Learning view-invariant sparse representations for cross-view action recognition. In ICCV, pages 3176-3183.
  30. Zheng, J., Jiang, Z., Phillips, P. J., and Chellappa, R. (2012). Cross-view action recognition via a transferable dictionary pair. In British Machine Vision Conference, pages 1-11.
  31. Zivkovic, Z. (2004). Improved adaptive gaussian mixture model for background subtraction. In ICPR, volume 2, pages 28-31.
Download


Paper Citation


in Harvard Style

Noceti N., Sciutti A., Rea F., Odone F. and Sandini G. (2015). Estimating Human Actions Affinities Across Views . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 130-137. DOI: 10.5220/0005307801300137


in Bibtex Style

@conference{visapp15,
author={Nicoletta Noceti and Alessandra Sciutti and Francesco Rea and Francesca Odone and Giulio Sandini},
title={Estimating Human Actions Affinities Across Views},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={130-137},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005307801300137},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Estimating Human Actions Affinities Across Views
SN - 978-989-758-090-1
AU - Noceti N.
AU - Sciutti A.
AU - Rea F.
AU - Odone F.
AU - Sandini G.
PY - 2015
SP - 130
EP - 137
DO - 10.5220/0005307801300137