Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

CVPR 2018 Xuanyi DongShoou-I YuXinshuo WengShih-En WeiYi YangYaser Sheikh

In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Our key observation is that the detections of the same landmark in adjacent frames should be coherent with registration, i.e., optical flow... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Facial Landmark Detection 300-VW (C) CPM+SBR+PAM AUC0.08 private 59.39 # 1
Facial Landmark Detection 300-VW (C) CPM+SBR AUC0.08 private 58.22 # 2