In the image restoration task, generative adversarial network (GAN) demonstrates excellent performance. However, there remain significant challenges concerning task of face region inpainting. Traditional model approaches are ineffective in maintaining global consistency among facial components and recovering fine details. To address this challenge, study proposes a generation combined transform...

OBJECTIVES Recent research suggests that older adults have difficulties with aspects of configural face processing. The present study examined whether age-related declines in sensitivity to configural face information are dependent on the face region in which configural changes occur. METHOD Younger and older adults completed a face-matching task that required the detection of configural mani...

Contrast-related signals from the eye region are known to be important for the processing of facial identity. Individuals with developmental prosopagnosia (DP) have severe face recognition problems, which may be linked to deficits in the perceptual processing of identity-related information from the eyes. We tested this hypothesis by measuring N170 components in DP participants and age-matched ...

Face detection has achieved great success using the region-based methods. In this report, we propose a region-based face detector applying deep networks in a fully convolutional fashion, named Face R-FCN. Based on Region-based Fully Convolutional Networks (R-FCN), our face detector is more accurate and computationally efficient compared with the previous R-CNN based face detectors. In our appro...