20 citations · 65 across the 18 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CV2021
PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
Jue Wang, Shaoli Huang, Xinchao Wang +1
Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning…
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…