Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Zongyong Deng"'
Publikováno v:
Wireless Communications and Mobile Computing, Vol 2021 (2021)
Although label distribution learning has made significant progress in the field of face age estimation, unsupervised learning has not been widely adopted and is still an important and challenging task. In this work, we propose an unsupervised contras
Autor:
Hao Liu, Zongyong Deng
Publikováno v:
Neurocomputing. 453:790-800
In this paper, we propose a geometry-attentive relational reasoning approach to investigate the problem of robust facial landmark detection, especially when faces were captured in wild conditions. Unlike existing methods which usually cannot explicit
Publikováno v:
CVPR
In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns adequate instances to outline its data distribution, likely leading to
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783030880064
PRCV (2)
PRCV (2)
In this paper, we propose a variational deep representation learning (VDRL) approach for cross-modal retrieval. Numerous existing methods map the image and text to the point representations, which is challenging to model the semantic multiplicity of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de57191cc41d2b0e2ba1e8c48795f38e
https://doi.org/10.1007/978-3-030-88007-1_41
https://doi.org/10.1007/978-3-030-88007-1_41
Publikováno v:
ICME
In this paper, we propose to learn a neighborhood-reasoning label distribution (NRLD) for facial age estimation. Unlike conventional label distribution methods with fixed-structural aging patterns, in this work, our NRLD aims to reason about more res
Publikováno v:
Pattern Recognition. 107:107354
In this paper, we propose a spatial-temporal deformable networks approach to investigate both problems of face alignment in static images and face tracking in videos under unconstrained environments. Unlike conventional feature extractions which cann