no code implementations • 1 Dec 2023 • Kerui Gu, Zhihao LI, Shiyong Liu, Jianzhuang Liu, Songcen Xu, Youliang Yan, Michael Bi Mi, Kenji Kawaguchi, Angela Yao
Estimating 3D rotations is a common procedure for 3D computer vision.
no code implementations • 28 Nov 2023 • Kerui Gu, Rongyu Chen, Angela Yao
Most 2D human pose estimation frameworks estimate keypoint confidence in an ad-hoc manner, using heuristics such as the maximum value of heatmaps.
no code implementations • 25 Jan 2023 • Kerui Gu, Linlin Yang, Michael Bi Mi, Angela Yao
Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.
no code implementations • CVPR 2023 • Qiyuan He, Linlin Yang, Kerui Gu, Qiuxia Lin, Angela Yao
We present Pose Integrated Gradient (PoseIG), the first interpretability technique designed for pose estimation.
no code implementations • ICLR 2022 • Kerui Gu, Linlin Yang, Angela Yao
We do a deep dive on the inference and back-propagation of integral pose regression to better understand the causes behind the performance and training differences.
no code implementations • ICCV 2021 • Kerui Gu, Linlin Yang, Angela Yao
Heatmap-based detection methods are dominant for 2D human pose estimation even though regression is more intuitive.