Pose Estimation Comparison Hub
4 papers - avg viability 6.8
Top Papers
- CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation(9.0)
CIGPose leverages causal intervention to enhance whole-body pose estimation, achieving state-of-the-art accuracy with robust performance in challenging scenes.
- mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud(8.0)
mmGAT leverages mmWave radar and Graph Neural Networks to achieve state-of-the-art human pose estimation, offering a privacy-preserving and light-insensitive alternative to image-based methods.
- Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation(8.0)
TAR-ViTPose enhances video-based human pose estimation by aggregating temporal cues, offering more robust and accurate predictions than existing methods.
- Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching(2.0)
A novel metric for evaluating multi-person pose estimation that balances true-positive and false-positive detections.