Abstract
The problem of evaluating a person’s posture from video data is solved. Various key points of the human body are analyzed. We study the change in the accuracy of a fixed model when using different proportions in the regularization term of the loss function. It is shown that for a fixed number of training epochs, the accuracy of the model differs depending on the selected proportions. In addition, it is shown that the linear correlation between the trajectories of the key points that are part of the regularization term is not the main criterion for predicting the effectiveness of applying the regularization term of the loss function.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Change history
12 January 2024
An Erratum to this paper has been published: https://doi.org/10.1134/S1064230723330018
REFERENCES
V. Vapnik and A. Vashist, “A new learning paradigm: learning using privileged information,” Neur. Networks 22, 544–557 (2009).
A. Lehrmann, P. Gehler, and S. Nowozin, “A Non-Parametric Bayesian Network Prior of Human Pose,” in Proc. IEEE Int. Conf. on Computer Vision (Sydney, 2013), pp. 1281–1288.
C. Ionescu, D. Papava, V. Olaru, and C. Sminchisescu, “Human 3.6m: Large scale datasets and predictive methods for 3D human sensing in natural environments,” IEEE Trans. Pattern Anal. Mach. Intell. 36, 1325–1339 (2013).
A. Ignatov and V. Strijov, “Human activity recognition using quasiperiodic time series collected from a single tri-axial accelerometer,” Multimedia Tools Appl. 75, 7257–7270 (2016).
A. Katrutsa and V. Strijov, “Stress test procedure for feature selection algorithms,” Chemom. Intell. Lab. Syst. 142, 172–183 (2015).
O. Cliff, J. Lizier, N. Tsuchiya, and B. Fulcher, “Unifying pairwise interactions in complex dynamics,” 2022. https://arxiv.org/pdf/2201.11941.
M. Trumble, A. Gilbert, C. Malleson, A. Hilton, and J. Collomosse, “Total capture: 3D human pose estimation fusing video and inertial sensors,” in Proc. of 28th British Machine Vision Conference (London, 2017), pp. 1–13.
P. Márquez-Neila, M. Salzmann, and P. Fua, “Imposing hard constraints on deep networks: Promises and limitations”, 2017. https://arxiv.org/pdf/1706.02025.
G. de Luca, T. Lampoltshammer, and J. Scholz, “How many equations of motion describe a moving human?,” 2022. https://arxiv.org/pdf/2207.14331.
C. Zheng, S. Zhu, M. Mendieta, T. Yang, C. Chen, and Z. Ding, “3D human pose estimation with spatial and temporal transformers,” in Proc. IEEE/CVF Int. Conf. on Computer Vision (Montreal, 2021), pp. 11656–11665.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kaprielova, M.S., Neichev, R.G. & Tikhonova, A.D. Privileged Learning Using Regularization in the Problem of Evaluating the Human Posture. J. Comput. Syst. Sci. Int. 62, 538–541 (2023). https://doi.org/10.1134/S1064230723030061
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064230723030061