Yanlu Cai — accepted AI-conference papers

2024

FusionFormer: A Concise Unified Feature Fusion Transformer for 3D Pose Estimation

Yanlu Cai, Weizhong Zhang, Yuan Wu, Cheng Jin

AAAI 2024technical

Depth uncertainty is a core challenge in 3D human pose estimation, especially when the camera parameters are unknown. Previous methods try to reduce the impact of depth uncertainty by multi-view and/or multi-frame feature fusion to utilize more spatial and temporal information. However, they general…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2024

PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization

Yanlu Cai, Weizhong Zhang, Yuan Wu, Cheng Jin

CVPR 2024poster

Camera-parameter-free multi-view pose estimation is an emerging technique for 3D human pose estimation (HPE). They can infer the camera settings implicitly or explicitly to mitigate the depth uncertainty impact showcasing significant potential in real applications. However due to the limited camera…

Cited by 3 Source ↗PDF ↗Scholar ↗