activity
20182021
most citedAccurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture

18 citations · 29 across the 8 of their papers we have counts for

collaborators

12 papers

cs.CV20213 cited

ShapeEditer: a StyleGAN Encoder for Face Swapping

Shuai Yang, Kai Qiao

In this paper, we propose a novel encoder, called ShapeEditor, for high-resolution, realistic and high-fidelity face exchange. First of all, in order to ensure sufficient clarity a…

cs.LG20213 cited

Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout

Pengfei Xie, Linyuan Wang, Ruoxi Qin +4

Deep neural networks(DNNs) is vulnerable to be attacked by adversarial examples. Black-box attack is the most threatening attack. At present, black-box attack methods mainly adopt…

cs.LG2020

Defense-guided Transferable Adversarial Attacks

Zifei Zhang, Kai Qiao, Jian Chen +1

Though deep neural networks perform challenging tasks excellently, they are susceptible to adversarial examples, which mislead classifiers by applying human-imperceptible perturbat…

cs.CV2020

Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features

Kai Qiao, Chi Zhang, Jian Chen +3

On basis of functional magnetic resonance imaging (fMRI), researchers are devoted to designing visual encoding models to predict the neuron activity of human in response to present…

cs.CV2020

BigGAN-based Bayesian reconstruction of natural images from human brain activity

Kai Qiao, Jian Chen, Linyuan Wang +3

In the visual decoding domain, visually reconstructing presented images given the corresponding human brain activity monitored by functional magnetic resonance imaging (fMRI) is di…

cs.CV2020

AdvJND: Generating Adversarial Examples with Just Noticeable Difference

Zifei Zhang, Kai Qiao, Lingyun Jiang +2

Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial exampl…