Robust and precise facial landmark detection by self-calibrated pose attention network
Current fully supervised facial landmark detection methods have progressed rapidly and
achieved remarkable performance. However, they still suffer when coping with faces under …
achieved remarkable performance. However, they still suffer when coping with faces under …
Unsupervised eyeglasses removal in the wild
Eyeglasses removal is challenging in removing different kinds of eyeglasses, eg, rimless
glasses, full-rim glasses, and sunglasses, and recovering appropriate eyes. Due to the …
glasses, full-rim glasses, and sunglasses, and recovering appropriate eyes. Due to the …
Modal-regression-based broad learning system for robust regression and classification
A novel neural network, namely, broad learning system (BLS), has shown impressive
performance on various regression and classification tasks. Nevertheless, most BLS models …
performance on various regression and classification tasks. Nevertheless, most BLS models …
Siamese networks with an online reweighted example for imbalanced data learning
L Zhao, Z Shang, J Tan, M Zhou, M Zhang, D Gu… - Pattern Recognition, 2022 - Elsevier
One key challenging problem in data mining and decision-making is to establish a decision
support system based on unbalanced datasets. In this study, we propose a novel algorithm …
support system based on unbalanced datasets. In this study, we propose a novel algorithm …
Noise-related face image recognition based on double dictionary transform learning
M Liao, X Fan, Y Li, M Gao - Information Sciences, 2023 - Elsevier
The existing single dictionary learning algorithms are applied to face recognition and
achieve satisfactory results. However, their performance is poor when dealing with noisy …
achieve satisfactory results. However, their performance is poor when dealing with noisy …
Bioinformatics analysis of potential pathogenesis and risk genes of immunoinflammation-promoted renal injury in severe COVID-19
Z Chen, C Chen, F Chen, R Lan, G Lin… - Frontiers in …, 2022 - frontiersin.org
Renal injury secondary to COVID-19 is an important factor for the poor prognosis of COVID-
19 patients. The pathogenesis of renal injury caused by aberrant immune inflammatory of …
19 patients. The pathogenesis of renal injury caused by aberrant immune inflammatory of …
Simultaneous robust matching pursuit for multi-view learning
Joint sparse representation (JSR) has attracted massive attention with many successful
applications in pattern recognition recently. In this paper, we propose a novel robust multi …
applications in pattern recognition recently. In this paper, we propose a novel robust multi …
Fm-3dfr: Facial manipulation-based 3-d face reconstruction
S Zhao, X Wang, D Zhang, G Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
3-D Morphable model (3DMM) has widely benefited 3-D face-involved challenges given its
parametric facial geometry and appearance representation. However, previous 3-D face …
parametric facial geometry and appearance representation. However, previous 3-D face …
Joint optimal transport with convex regularization for robust image classification
J Qian, WK Wong, H Zhang, J Xie… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
The critical step of learning the robust regression model from high-dimensional visual data is
how to characterize the error term. The existing methods mainly employ the nuclear norm to …
how to characterize the error term. The existing methods mainly employ the nuclear norm to …
Robust multi-view learning via M-estimator joint sparse representation
Recently, multi-view learning has achieved extraordinary success in many research areas
such as pattern recognition and data mining. Most existing multi-view methods mainly focus …
such as pattern recognition and data mining. Most existing multi-view methods mainly focus …