activity
20192022
most citedNot All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts

14 citations · 29 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV20224 cited

CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data

Ke Zhang, Jin Fan, Shaoli Huang +3

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing correspon…

cs.CV2021

Structure-Aware Feature Generation for Zero-Shot Learning

Lianbo Zhang, Shaoli Huang, Xinchao Wang +2

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior…

cs.CV20208 cited

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Shaoli Huang, Xinchao Wang, Dacheng Tao

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative…

cs.CV20193 cited

An End-to-end Framework for Unconstrained Monocular 3D Hand Pose Estimation

Sanjeev Sharma, Shaoli Huang, Dacheng Tao

This work addresses the challenging problem of unconstrained 3D hand pose estimation using monocular RGB images. Most of the existing approaches assume some prior knowledge of hand…

cs.CV201914 cited

Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts

Jue Wang, Shaoli Huang, Xinchao Wang +1

Not all the human body parts have the same~degree of freedom~(DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does.…