SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition
Open paper
Benchmark
Model
Rank
Results
action-recognition-on-h2o-2-hands-and-objects
SHARP
#2
Actions Top-1: 91.73
RGB: No
Hand Pose: 3D
Object Pose: 2D
…
skeleton-based-action-recognition-on-h2o
SHARP
#2
Accuracy: 91.73
Rank counts only results with a code link.