11 citations · 19 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CV2023★ 2 cited
DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation
Runyang Feng, Yixing Gao, Tze Ho Elden Tse +2
Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection…
cs.CV2023
Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
Runyang Feng, Yixing Gao, Xueqing Ma +2
Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fie…