Search Results for author: Xuan Cao

Found 7 papers, 3 papers with code

Adversarial Refinement Network for Human Motion Prediction

no code implementations23 Nov 2020 Xianjin Chao, Yanrui Bin, Wenqing Chu, Xuan Cao, Yanhao Ge, Chengjie Wang, Jilin Li, Feiyue Huang, Howard Leung

Specifically, we take both the historical motion sequences and coarse prediction as input of our cascaded refinement network to predict refined human motion and strengthen the refinement network with adversarial error augmentation.

Human motion prediction motion prediction

Bayesian Group Selection in Logistic Regression with Application to MRI Data Analysis

1 code implementation4 Dec 2019 Kyoungjae Lee, Xuan Cao

We consider Bayesian logistic regression models with group-structured covariates.


Anti-Confusing: Region-Aware Network for Human Pose Estimation

no code implementations3 May 2019 Xuan Cao, Yanhao Ge, Ying Tai, Wei zhang, Jian Li, Chengjie Wang, Jilin Li, Feiyue Huang

In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation.

Data Augmentation Pose Estimation

Consistent Bayesian Sparsity Selection for High-dimensional Gaussian DAG Models with Multiplicative and Beta-mixture Priors

2 code implementations8 Mar 2019 Xuan Cao, Kshitij Khare, Malay Ghosh

Estimation of the covariance matrix for high-dimensional multivariate datasets is a challenging and important problem in modern statistics.

Statistics Theory Methodology Statistics Theory

Sparse Photometric 3D Face Reconstruction Guided by Morphable Models

no code implementations CVPR 2018 Xuan Cao, Zhang Chen, Anpei Chen, Xin Chen, Cen Wang, Jingyi Yu

We present a novel 3D face reconstruction technique that leverages sparse photometric stereo (PS) and latest advances on face registration/modeling from a single image.

3D Face Reconstruction Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.