TransfHAR at UIST 2026: self-supervised wrist motions enable on-watch custom activity recognition
realkaranahuja · x · 2026-11-01
TransfHAR, to appear at UIST 2026, uses self-supervised learning on coarse wrist motions transferred to fine-grained activity recognition, letting users define new activities with a few demonstrations and recognize them in real time on a smartwatch.
More from Embodied
- Developer dresses robot 'Bob' as a ghost to hand out Halloween candy — chrismatthieu · 2026-11-01
- GRASP authors compare with SuperMimic: extracting more optimization signal from sim experience — hankyang94 · 2026-11-01
- Harvard's GRASP refines human demos in physics sim for dexterous hands and Unitree G1 — hankyang94 · 2026-11-01
- Neuralink user designs 3D-printed parts with thoughts alone, holds them hours later — Scobleizer · 2026-11-01
- "Doesn't need tactile" vs "won't benefit from tactile" are different worlds, researcher argues — _krishna_murthy · 2026-11-01
- Tesla FSD spots reckless street racer on blind corner, avoids crash with kids aboard — WilliamWangNLP · 2026-11-01