RadProPoser uses a variational encoder-decoder with spectral attention to predict 3D poses and aleatoric uncertainties from radar tensors, achieving 6.425 cm MPJPE on a new benchmark and 5.042 cm on HuPR with calibrated uncertainties.
Accurate uncertainties for deep learning using calibrated regression,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2representative citing papers
ODiSAR uses a Transformer digital twin with reconstruction error and Monte Carlo dropout to detect OOD events in self-adaptive robots, reporting up to 98% AUROC on office navigation and maritime ship tasks.
citing papers explorer
-
RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits
RadProPoser uses a variational encoder-decoder with spectral attention to predict 3D poses and aleatoric uncertainties from radar tensors, achieving 6.425 cm MPJPE on a new benchmark and 5.042 cm on HuPR with calibrated uncertainties.
-
Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
ODiSAR uses a Transformer digital twin with reconstruction error and Monte Carlo dropout to detect OOD events in self-adaptive robots, reporting up to 98% AUROC on office navigation and maritime ship tasks.