activity
20182021
most citedAdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

113 citations · 146 across the 9 of their papers we have counts for

collaborators

13 papers

cs.CV2021

Nuisance-Label Supervision: Robustness Improvement by Free Labels

Xinyue Wei, Weichao Qiu, Yi Zhang +2

In this paper, we present a Nuisance-label Supervision (NLS) module, which can make models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a tas…

cs.CV20212 cited

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation

Jiteng Mu, Weichao Qiu, Adam Kortylewski +3

Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been d…

cs.CV202015 cited

Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation

Qihao Liu, Weichao Qiu, Weiyao Wang +2

We propose an unsupervised vision-based system to estimate the joint configurations of the robot arm from a sequence of RGB or RGB-D images without knowing the model a priori, and…

cs.CV2020113 cited

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

Zhe Zhang, Chunyu Wang, Weichao Qiu +2

Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make…

cs.CV20192 cited

Identity Preserve Transform: Understand What Activity Classification Models Have Learnt

Jialing Lyu, Weichao Qiu, Xinyue Wei +3

Activity classification has observed great success recently. The performance on small dataset is almost saturated and people are moving towards larger datasets. What leads to the p…

cs.CV2019

Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints

Pengfei Li, Weichao Qiu, Michael Peven +2

Scene context is a powerful constraint on the geometry of objects within the scene in cases, such as surveillance, where the camera geometry is unknown and image quality may be poo…