PredCNN

Reported on 8 benchmarks across 4 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

3D Human Pose EstimationonFiltered NTU RGB+D
MAE
1.6394
best: 1.1651 (PISEP^2 (L1 norm))
3D Human Pose EstimationonFiltered NTU RGB+D
MSE
0.1665
best: 0.121 (PISEP^2 (L1 norm))
Pose EstimationonFiltered NTU RGB+D
MAE
1.6394
best: 1.1651 (PISEP^2 (L1 norm))
Pose EstimationonFiltered NTU RGB+D
MSE
0.1665
best: 0.121 (PISEP^2 (L1 norm))

Methodology2 results

3DonFiltered NTU RGB+D
MAE
1.6394
best: 1.1651 (PISEP^2 (L1 norm))
3DonFiltered NTU RGB+D
MSE
0.1665
best: 0.121 (PISEP^2 (L1 norm))

Audio2 results

1 Image, 2*2 StitchionFiltered NTU RGB+D
MAE
1.6394
best: 1.1651 (PISEP^2 (L1 norm))
1 Image, 2*2 StitchionFiltered NTU RGB+D
MSE
0.1665
best: 0.121 (PISEP^2 (L1 norm))