Search Results for author: Xueqing Ma

Found 2 papers, 0 papers with code

DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation

no code implementations ICCV 2023 Runyang Feng, Yixing Gao, Tze Ho Elden Tse, Xueqing Ma, Hyung Jin Chang

However, extending such models to multi-frame human pose estimation is non-trivial due to the presence of the additional temporal dimension in videos.

Denoising Image Generation +5

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

no code implementations CVPR 2023 Runyang Feng, Yixing Gao, Xueqing Ma, Tze Ho Elden Tse, Hyung Jin Chang

On the other hand, the temporal difference has the ability to encode representative motion information which can potentially be valuable for pose estimation but has not been fully exploited.

Disentanglement Optical Flow Estimation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.