人工智能
计算机科学
凝视
特征提取
计算机视觉
特征(语言学)
面子(社会学概念)
单眼
深度学习
模式识别(心理学)
样品(材料)
任务(项目管理)
眼动
工程类
社会科学
哲学
系统工程
色谱法
社会学
语言学
化学
作者
Zichen Zhao,Weitao Ke,Qingsong Yan,Xiaofeng Lu
摘要
Appearance-based methods with deep learning can predict the point of gaze by using a monocular camera, which requires a large sample to learn. However, existing appearance-based gaze estimation methods with deep learning mainly use face and eye images or only use a single face image, ignoring the correlation between face features and eye features In response to this issue, we propose a coordination model where face feature extraction is the gaze estimation network and eye feature extraction is the coordination network, which deeply fuses the eye-face feature relationships to perform the gaze estimation task. The model achieves good results on MPIIFaceGaze dataset and GazeCapture dataset.
科研通智能强力驱动
Strongly Powered by AbleSci AI