Search Results for author: Hongxin Lin

Found 4 papers, 0 papers with code

AMPose: Alternately Mixed Global-Local Attention Model for 3D Human Pose Estimation

no code implementations9 Oct 2022 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).

3D Human Pose Estimation

Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis

no code implementations20 Oct 2019 Zelin Xiao, Hongxin Lin, Renjie Li, Hongyang Chao, Shengyong Ding

Interestingly, the principal component analysis exactly provides an effective way to define such a frame, i. e. setting the principal components as the frame axes.

Object Retrieval

Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables

no code implementations14 Aug 2019 Hongxin Lin, Zelin Xiao, Yang Tan, Hongyang Chao, Shengyong Ding

Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load.

Face Recognition from Sequential Sparse 3D Data via Deep Registration

no code implementations23 Oct 2018 Yang Tan, Hongxin Lin, Zelin Xiao, Shengyong Ding, Hongyang Chao

However, such devices only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly.

Face Recognition

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