Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions
Open paper
Benchmark
Model
Rank
Results
3d-human-pose-estimation-on-human36m
Attention (T=243 CPN)
–
Average MPJPE (mm): 44.8
Using 2D ground-truth joints: No
…
3d-human-pose-estimation-on-humaneva-i
Attention (T=27 MA)
–
Mean Reconstruction Error (mm): 15.4
Rank counts only results with a code link.