Conference
2026
SGAFormer: Skeleton-Graph and Agent-guided Transformer network for monocular video-based 3D human pose estimation
Ex-periments show that SGAFormer remains competitive under detected 2D keypoint inputs, achieves superior temporal consistency, and ob-tains strong upper-bound performance with ground-truth 2D keypoints, demon-strating the effectiveness of the proposed spatial-temporal modeling frame-work.
Min Li
· Poster Volume 0007 The 2026... · 0 citations