26 citations · 29 across the 7 of their papers we have counts for
8 papers
MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulation
Ziliang Xiong, Henglin Shi, Per-Erik Forssen
Conventional algebraic triangulation solves 3D human pose estimation (HPE) from multi-view 2D keypoints. The typical approach, decoding 2D keypoints from predicted heatmaps, is unr…
Commutator-Induced Uncertainty in VAEs
Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen +1
Variational autoencoders (VAEs) often struggle to represent non-commutative structure in learned latent spaces. Symmetry-aware VAEs commonly address this issue by enforcing commuta…
MATTER: Multiscale Attention for Registration Error Regression
Shipeng Liu, Ziliang Xiong, Khac-Hoang Ngo +1
Point cloud registration (PCR) is crucial for many downstream tasks, such as simultaneous localization and mapping (SLAM) and object tracking. This makes detecting and quantifying…
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
Shipeng Liu, Ziliang Xiong, Bastian Wandt +1
Human Pose Estimation (HPE) is increasingly important for applications like virtual reality and motion analysis, yet current methods struggle with balancing accuracy, computational…
Collision Risk Estimation via Loss Prediction in End-to-End Autonomous Driving
Ziliang Xiong, Shipeng Liu, Nathaniel Helgesen +3
Collision risk estimation and avoidance play central roles in the safety of autonomous driving (AD) systems. Recently emerged end-to-end AD systems gain collision avoidance ability…
Uncertainty Quantification Metrics for Deep Regression
Simon Kristoffersson Lind, Ziliang Xiong, Per-Erik Forssén +1
When deploying deep neural networks on robots or other physical systems, the learned model should reliably quantify predictive uncertainty. A reliable uncertainty allows downstream…