Search Results for author:
Found 2 papers, 2 papers with code
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos
Previous video-based human pose estimation methods have shown promising results by leveraging aggregated features of consecutive frames.
Ranked #1 on
Pose Estimation
on J-HMDB
OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos
We achieve state-of-the-art pose estimation results for PoseTrack2017 and PoseTrack2018 datasets and demonstrate the robustness of our approach to occlusion and motion blur in sparsely annotated video data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
