EHPNet

Reported on 6 benchmarks across 3 tasks · 1 paper

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

Computer Vision2 results

Pose EstimationonAFLW2000
MAE· 2022-10-25
4.15
best: 3.15 (OpNet)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705
Pose EstimationonBIWI
MAE (trained with BIWI data)· 2022-10-25
3.43
best: 1.413 (VGGNet-RNN)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705

Methodology2 results

3DonAFLW2000
MAE· 2022-10-25
4.15
best: 3.15 (OpNet)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705
3DonBIWI
MAE (trained with BIWI data)· 2022-10-25
3.43
best: 1.413 (VGGNet-RNN)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705

Audio2 results

1 Image, 2*2 StitchionAFLW2000
MAE· 2022-10-25
4.15
best: 3.15 (OpNet)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705
1 Image, 2*2 StitchionBIWI
MAE (trained with BIWI data)· 2022-10-25
3.43
best: 1.413 (VGGNet-RNN)
An Effective Deep Network for Head Pose Estimation without Keypoints arXiv:2210.13705