IEEE Style Citation: Rohini G. Bhaisare, S.S. Ponde, “Age Estimation Using Fixed Rank Representation (FRR),” International Journal of Computer Sciences and Engineering, Vol.7, Issue.12, pp.35-40, 2019.
MLA Style Citation: Rohini G. Bhaisare, S.S. Ponde "Age Estimation Using Fixed Rank Representation (FRR)." International Journal of Computer Sciences and Engineering 7.12 (2019): 35-40.
APA Style Citation: Rohini G. Bhaisare, S.S. Ponde, (2019). Age Estimation Using Fixed Rank Representation (FRR). International Journal of Computer Sciences and Engineering, 7(12), 35-40.
BibTex Style Citation:
@article{Bhaisare_2019,
author = {Rohini G. Bhaisare, S.S. Ponde},
title = {Age Estimation Using Fixed Rank Representation (FRR)},
journal = {International Journal of Computer Sciences and Engineering},
issue_date = {12 2019},
volume = {7},
Issue = {12},
month = {12},
year = {2019},
issn = {2347-2693},
pages = {35-40},
url = {https://www.ijcseonline.org/full_paper_view.php?paper_id=4970},
doi = {https://doi.org/10.26438/ijcse/v7i12.3540}
publisher = {IJCSE, Indore, INDIA},
}
RIS Style Citation:
TY - JOUR
DO = {https://doi.org/10.26438/ijcse/v7i12.3540}
UR - https://www.ijcseonline.org/full_paper_view.php?paper_id=4970
TI - Age Estimation Using Fixed Rank Representation (FRR)
T2 - International Journal of Computer Sciences and Engineering
AU - Rohini G. Bhaisare, S.S. Ponde
PY - 2019
DA - 2019/12/31
PB - IJCSE, Indore, INDIA
SP - 35-40
IS - 12
VL - 7
SN - 2347-2693
ER -
VIEWS
PDF
XML
459
410 downloads
235 downloads
Abstract
As it is an important and challenging problem in computer vision, face age estimation is typically cast as a classification or regression problem over a set of face samples with several ordinal age labels which have intrinsically cross-age correlations across adjacent age dimensions. As an outcome, these such correlations normally lead to age label ambiguities of face samples. Each face sample is associated with a latent label distribution that encodes the cross-age correlation information on label ambiguities. As we propose a totally data-driven distribution learning, approach to adaptively learn the latent label distributions. The proposed approach is capable of effectively discovering the intrinsic age distribution patterns for cross-age correlation analysis on the any prior assumptions on the forms of label distribution learning, this approach is able to flexible model of sample-specific context aware label distribution properties by solving a multi-task problem which jointly optimizes the tasks of age-label distribution learning and age prediction for individuals. Experimental outcomes demonstrate effectiveness of our approach.
Key-Words / Index Term
Age estimation, subspace learning, label distribution learning
References
[1] C.Zhang and G. Guo “Exploiting Unlabeled Ages For aging Pattern Analysis on a Large Databases”in Proc. IEEE Conf. Computer June 2013.
[2] C-G.Li and R.Vidal, “Structured sparse subspace clustering:A unified optimization framework,”in Proc.IEEE Conf Comput.Vis Pattern Recognition June 2015.
[3] X.Geng, “Label Distribution Learing” IEEE Trans. Knowl. Data July 2016
[4] “Deepface closing the gap to human level performance in face verification” Y.Taigman, M.Yang, M.Ranzato, and L.Wolf, in Proc .IEEE Conf. June 2014.
[5] X.Geng, C.Yin, and Z.H. Zhou, “Facial age estimation by learing from label distributions” IEEE Trans. Oct.2013.
[6] X.Geng, K. Smith Miles, and Z.H. Zhou X. Geng, “Facial age estimation by nonlinear aging pattern subspace” in proc. 16th ACM Int Conf. Oct. 2008.
[7] G.Liu, Z.Lin, S.Yan ,J.Sun, Y,Yu and Y.ma “Robust recovery of subspace structure by low rank representation” IEEE Trans. Jan. 2013.
[8] B.Xiao, X. Yang, Y.Xu and H.Zha “Learing Distance Metric For Regression By Semidefinite Programming with application to human age estimation” in Proc. 17th ACM in Proc 17th ACM Oct. 2009.
[9] C.G.Li and R.Vidal, “Structured sparse subspace clustering a unified optimization framework” in Proc.IEEE Conf. computer vis. Pattern June 2015.
VIEWS
PDF 
XML 
