论文标题
凝视网络：使用胶囊网络基于外观的凝视估算
Gaze-Net: Appearance-Based Gaze Estimation using Capsule Networks
论文作者
论文摘要
关于基于外观的凝视估计的最新研究表明，神经网络从包含姿势信息的面部图像中解码视线信息的能力。在本文中，我们提出了凝视网络：能够解码，表示和估计眼部图像的凝视信息的胶囊网络。我们使用两个公开可用的数据集（野外的200,000多个图像）和Columbia Caze（5000多个用户的图像，在5个相机角度/位置观察到21个凝视方向）评估了我们提出的系统。我们的模型实现了MPI-Igaze数据集中数据集中的合并角度误差估算值的平均绝对误差（MAE）为2.84 $^\ circ $。此外，Model的MAE为10.04 $^\ circ $，用于整个数据集注视估计数据集的错误。通过转移学习，错误将减少到5.9 $^\ CIRC $。结果表明，这种方法有希望，对使用商品网络摄像头开发低成本的多用户凝视跟踪系统的影响很有希望。
Recent studies on appearance based gaze estimation indicate the ability of Neural Networks to decode gaze information from facial images encompassing pose information. In this paper, we propose Gaze-Net: A capsule network capable of decoding, representing, and estimating gaze information from ocular region images. We evaluate our proposed system using two publicly available datasets, MPIIGaze (200,000+ images in the wild) and Columbia Gaze (5000+ images of users with 21 gaze directions observed at 5 camera angles/positions). Our model achieves a Mean Absolute Error (MAE) of 2.84$^\circ$ for Combined angle error estimate within dataset for MPI-IGaze dataset. Further, model achieves a MAE of 10.04$^\circ$ for across dataset gaze estimation error for Columbia gaze dataset. Through transfer learning, the error is reduced to 5.9$^\circ$. The results show this approach is promising with implications towards using commodity webcams to develop low-cost multi-user gaze tracking systems.
