Reproduce “A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jonas Leo Mueller, Dario Zanca, Sebastian Hoefler, Jan Petermann, Thomas Altstidl, Naga Venkata Sai Jitin Jami, Emmanuelle Salin, Bjoern M. Eskofier
The authors pretrain a shared encoder on unlabeled multi-radar data aligned to a common grid, then freeze it and train a small task-specific classifier. In subject-disjoint CI4R-Gait, with the target radar excluded from pretraining, the system averages 69.3% accuracy across four held-out subjects, versus 61.0% for RadMamba. This result is specific to that evaluation and does not isolate the cause.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.