EgoEMG is a new synchronized dataset of bilateral 16-channel EMG, egocentric vision, and mocap data covering over 10 hours from 41 people across 60 gestures, with benchmarks for EMG-to-pose, vision-to-pose, and fusion tasks.
For each pixel covered by a triangle, the interpolated depth is stored if it is smaller than the current buffer value
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EgoEMG: A Multimodal Egocentric Dataset with Bilateral EMG and Vision for Hand Pose Estimation
EgoEMG is a new synchronized dataset of bilateral 16-channel EMG, egocentric vision, and mocap data covering over 10 hours from 41 people across 60 gestures, with benchmarks for EMG-to-pose, vision-to-pose, and fusion tasks.