3 papers
cs.CV2025
Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation
Zenghao Zheng, Lianping Yang, Jinshan Pan +1
Transformer-based methods for 3D human pose estimation face significant computational challenges due to the quadratic growth of self-attention mechanism complexity with sequence le…
cs.CV2025
Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation
Zenghao Zheng, Lianping Yang, Hegui Zhu +1
Transformer-based 3D human pose estimation methods suffer from high computational costs due to the quadratic complexity of self-attention with respect to sequence length. Additiona…
cs.CV2025
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
Mingrui Ye, Lianping Yang, Hegui Zhu +3
This paper introduces a novel approach to monocular 3D human pose estimation using contextualized representation learning with the Transformer-GCN dual-stream model. Monocular 3D h…