Publications (7)
AMPose: Alternately Mixed Global-Local Attention Model for 3D Human Pose Estimation
Hongxin Lin, Yunwei Chiu, Peiyuan Wu
The graph convolutional networks (GCNs) have been applied to model the physically connected and non-local relations among human joints for 3D human pose estimation (HPE). In additi…
Face Recognition from Sequential Sparse 3D Data via Deep Registration
Yang Tan, Hongxin Lin, Zelin Xiao +2
Previous works have shown that face recognition with high accurate 3D data is more reliable and insensitive to pose and illumination variations. Recently, low-cost and portable 3D…
Breast Ultrasound Tumor Generation via Mask Generator and Text-Guided Network:A Clinically Controllable Framework with Downstream Evaluation
Haoyu Pan, Hongxin Lin, Zetian Feng +6
The development of robust deep learning models for breast ultrasound (BUS) image analysis is significantly constrained by the scarcity of expert-annotated data. To address this lim…
Online Adaptive Real-Time Beamforming Design for Dynamic Environments in Cell-Free Systems
Guanghui Chen, Zheng Wang, Hongxin Lin +2
In this paper, we consider real-time beamforming design for dynamic wireless environments with varying channels and different numbers of access points (APs) and users in cell-free…
Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis
Zelin Xiao, Hongxin Lin, Renjie Li +2
In this paper, we propose a simple yet effective method to endow deep 3D models with rotation invariance by expressing the coordinates in an intrinsic frame determined by the objec…
Computationally Efficient Unsupervised Deep Learning for Robust Joint AP Clustering and Beamforming Design in Cell-Free Systems
Guanghui Chen, Zheng Wang, Hongxin Lin +2
In this paper, we consider robust joint access point (AP) clustering and beamforming design with imperfect channel state information (CSI) in cell-free systems. Specifically, we jo…