← Search

Xueqing Ma

2 accepted papers

2023

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

ICCV 2023poster

Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining attention in computer vision. However, extending such models to mu…

Cited by 43PDFScholar
2023

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

CVPR 2023poster

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 fields, which might incur numerous irrelevant cues, such as a nearby person or background. Without further efforts to excav…

Cited by 24SourcePDFScholar