JTA
Joint Track Auto
Videos
JTA is a dataset for people tracking in urban scenarios by exploiting a photorealistic videogame. It is up to now the vastest dataset (about 500.000 frames, almost 10 million body poses) of human body parts for people tracking in urban scenarios.
Source: Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World
Benchmarks
1 Image, 2*2 Stitchi/F1(t=0.4m)1 Image, 2*2 Stitchi/F1(t=0.8m)1 Image, 2*2 Stitchi/F1(t=1.2m)3D/F1(t=0.4m)3D/F1(t=0.8m)3D/F1(t=1.2m)3D Human Pose Estimation/F1(t=0.4m)3D Human Pose Estimation/F1(t=0.8m)3D Human Pose Estimation/F1(t=1.2m)Pose Estimation/F1(t=0.4m)Pose Estimation/F1(t=0.8m)Pose Estimation/F1(t=1.2m)