Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection

Open paper
Benchmark Model Rank Results
facial-landmark-detection-on-300wD-ViT#1NME: 2.85
facial-landmark-detection-on-wflwD-ViT#1NME: 3.75NME (inter-ocular): 3.75AUC@10 (inter-ocular): 63.7…

Rank counts only results with a code link.