WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

Benchmark Model Rank Results
head-pose-estimation-on-biwiWHENet-V#6MAE (trained with other data): 3.48
head-pose-estimation-on-biwiWHENet#11MAE (trained with other data): 3.81
head-pose-estimation-on-panopticWHENET#6Geodesic Error (GE): 24.38
head-pose-estimation-on-aflw2000WHENet-V#13MAE: 4.83
head-pose-estimation-on-aflw2000WHENet#18MAE: 5.42