Semiconductor Optoelectronics, Volume. 42, Issue 1, 93(2021)

Adaptive Gaze Estimation Based on Differential Convolution

LUO Yuan... CHEN Xu and OU Junxiong |Show fewer author(s)
Author Affiliations
  • [in Chinese]
  • show less

    An adaptive model is proposed for gaze estimation based on differential convolutional neural network. The adaptive model incorporates information of head pose and designs a network named Differential Network (DNet) by virtue of differential convolution. The DNet is trained to predict gaze differences in the eyes, calibrate the initial gaze estimations and thus reduce the estimation errors. Through validation on the publicly available dataset Eyediap and comparison with other well-performed gaze estimation models developed in recent years, the experimental results indicate that the proposed adaptive model can estimate gaze directions more accurately under free head movement.

    Tools

    Get Citation

    Copy Citation Text

    LUO Yuan, CHEN Xu, OU Junxiong. Adaptive Gaze Estimation Based on Differential Convolution[J]. Semiconductor Optoelectronics, 2021, 42(1): 93

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Aug. 16, 2020

    Accepted: --

    Published Online: Mar. 18, 2021

    The Author Email:

    DOI:10.16818/j.issn1001-5868.2021.01.017

    Topics