Leiye Liu — accepted AI-conference papers

2026

StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation

Jiahong Jiang, Miao Zhang, Leiye Liu, Yao Cui, Jingjing Li, Wei Ji +2

ICML 2026poster

Accurately modeling complex temporal and topological dependencies and depth information is critical for monocular 3D human pose estimation, yet existing Mamba-based approaches struggle to fulfill these demands, suffering from internal state update confusion induced by forced sequence flattening and …

Cited by 0 Source ↗Scholar ↗

2025

DefMamba: Deformable Visual State Space Model

Leiye Liu, Miao Zhang, Jihao Yin, Tingwei Liu, Wei Ji, Yongri Piao +1

CVPR 2025poster

Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods flatten images into 1D sequences using predefined scan orders,…

Cited by 1 Source ↗PDF ↗Scholar ↗