activity
20162023
most citedBoosting Fast Adversarial Training with Learnable Adversarial Initialization

69 citations · 510 across the 49 of their papers we have counts for

collaborators
Showing 2019 · cs.CVShow all

5 papers · 2 filters

cs.CV2019★ 22 cited

Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations

Yuezun Li, Xin Yang, Baoyuan Wu +1

Recent years have seen fast development in synthesizing realistic human faces using AI technologies. Such fake faces can be weaponized to cause negative personal and social impact.…

cs.CV2019★ 7 cited

Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables

Yan Xu, Baoyuan Wu, Fumin Shen +4

In this work, we study the robustness of a CNN+RNN based image captioning system being subjected to adversarial noises. We propose to fool an image captioning system to generate so…

cs.CV2019★ 15 cited

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

Yinpeng Dong, Hang Su, Baoyuan Wu +4

Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to ad…

cs.CV2019★ 31 cited

Target-Aware Deep Tracking

Xin Li, Chao Ma, Baoyuan Wu +2

Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vis…

cs.CV2019

Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning

Baoyuan Wu, Weidong Chen, Yanbo Fan +4

In existing visual representation learning tasks, deep convolutional neural networks (CNNs) are often trained on images annotated with single tags, such as ImageNet. However, a sin…