TY - JOUR
T1 - Human activity recognition using robust adaptive privileged probabilistic learning
AU - Vrigkas, Michalis
AU - Kazakos, Evangelos
AU - Nikou, Christophoros
AU - Kakadiaris, Ioannis A.
N1 - Funding Information:
This work has been co-funded by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH-CREATE-INNOVATE (Project Code: T1EDK-04517) and by the UH Hugh Roy and Lillie Cranz Cullen Endowment Fund.
Funding Information:
The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. All statements of fact, opinion or conclusions contained herein are those of the authors and should not be construed as representing the official views or policies of the sponsors.
Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature.
PY - 2021/8
Y1 - 2021/8
N2 - In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network.
AB - In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network.
KW - Hidden conditional random fields
KW - Human activity recognition
KW - Learning using privileged information
KW - Student’s t-distribution
UR - http://www.scopus.com/inward/record.url?scp=85098789566&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098789566&partnerID=8YFLogxK
U2 - 10.1007/s10044-020-00953-x
DO - 10.1007/s10044-020-00953-x
M3 - Article
AN - SCOPUS:85098789566
VL - 24
SP - 915
EP - 932
JO - Pattern Analysis and Applications
JF - Pattern Analysis and Applications
SN - 1433-7541
IS - 3
ER -