116 citations · 264 across the 41 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CV2021
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
Zhiwei Liu, Xiangyu Zhu, Lu Yang +7
3D human pose and shape recovery from a monocular RGB image is a challenging task. Existing learning based methods highly depend on weak supervision signals, e.g. 2D and 3D joint l…
cs.CV2021★ 116 cited
DPT: Deformable Patch-based Transformer for Visual Recognition
Zhiyang Chen, Yousong Zhu, Chaoyang Zhao +4
Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which…