Gan inversion: A survey
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …
model so that the image can be faithfully reconstructed from the inverted code by the …
Tedigan: Text-guided diverse face image generation and manipulation
In this work, we propose TediGAN, a novel framework for multi-modal image generation and
manipulation with textual descriptions. The proposed method consists of three components …
manipulation with textual descriptions. The proposed method consists of three components …
Investigating bias in facial analysis systems: A systematic review
Recent studies have demonstrated that most commercial facial analysis systems are biased
against certain categories of race, ethnicity, culture, age and gender. The bias can be traced …
against certain categories of race, ethnicity, culture, age and gender. The bias can be traced …
Apdrawinggan: Generating artistic portrait drawings from face photos with hierarchical gans
Significant progress has been made with image stylization using deep learning, especially
with generative adversarial networks (GANs). However, existing methods fail to produce …
with generative adversarial networks (GANs). However, existing methods fail to produce …
Under the veil of tolerance: A justification–suppression approach to anti-Islamic implicit bias in reaction to terrorist attacks.
Abstract Twenty years after 9/11, the impact of terrorism on social and political attitudes
remains unclear. Several large-scale surveys suggest that terrorism has no discernible …
remains unclear. Several large-scale surveys suggest that terrorism has no discernible …
Towards open-world text-guided face image generation and manipulation
The existing text-guided image synthesis methods can only produce limited quality results
with at most\mbox {$\text {256}^ 2$} resolution and the textual instructions are constrained in …
with at most\mbox {$\text {256}^ 2$} resolution and the textual instructions are constrained in …
Line drawings for face portraits from photos using global and local structure based GANs
Despite significant effort and notable success of neural style transfer, it remains challenging
for highly abstract styles, in particular line drawings. In this paper, we propose …
for highly abstract styles, in particular line drawings. In this paper, we propose …
When my actions shape your looks: Experience-based properties of approach/avoidance bias the visual representation of others.
The literature on the approach/avoidance training (AAT) effect has focused on its evaluative
consequences (with approached stimuli evaluated as more positive than avoided ones) …
consequences (with approached stimuli evaluated as more positive than avoided ones) …
It is not only whether I approach but also why I approach: A registered report on the role of action framing in approach/avoidance training effects
Research on approach/avoidance training (AAT) effects shows that approach (ie, reducing
the distance between the self and a stimulus) leads to more positive evaluations of stimuli …
the distance between the self and a stimulus) leads to more positive evaluations of stimuli …
Diverse Face Images (DFI): Validated for racial representation and eye gaze
Face processing is a central component of human communication and social engagement.
The present investigation introduces a set of racially and ethnically inclusive faces created …
The present investigation introduces a set of racially and ethnically inclusive faces created …