English

Gaze Estimation with an Ensemble of Four Architectures

Computer Vision and Pattern Recognition 2021-07-06 v1

Abstract

This paper presents a method for gaze estimation according to face images. We train several gaze estimators adopting four different network architectures, including an architecture designed for gaze estimation (i.e.,iTracker-MHSA) and three originally designed for general computer vision tasks(i.e., BoTNet, HRNet, ResNeSt). Then, we select the best six estimators and ensemble their predictions through a linear combination. The method ranks the first on the leader-board of ETH-XGaze Competition, achieving an average angular error of 3.113.11^{\circ} on the ETH-XGaze test set.

Keywords

Cite

@article{arxiv.2107.01980,
  title  = {Gaze Estimation with an Ensemble of Four Architectures},
  author = {Xin Cai and Boyu Chen and Jiabei Zeng and Jiajun Zhang and Yunjia Sun and Xiao Wang and Zhilong Ji and Xiao Liu and Xilin Chen and Shiguang Shan},
  journal= {arXiv preprint arXiv:2107.01980},
  year   = {2021}
}