Recent years have witnessed substantial progress in semantic image synth...
In this paper, we focus on tackling the precise keypoint coordinates
reg...
Deep neural networks (DNNs) are known to be vulnerable to backdoor attac...
Weakly-supervised object detection (WSOD) has emerged as an inspiring re...
Understanding complex social interactions among agents is a key challeng...
Recent deep generative models have achieved promising performance in ima...
Deep Neural Network classifiers are vulnerable to adversarial attack, wh...
A new unified video analytics framework (ER3) is proposed for complex ev...
For image inpainting, the convolutional neural networks (CNN) in previou...
Pedestrian trajectory prediction is a key technology in autopilot, which...
Recent studies unveil the vulnerabilities of deep ranking models, where ...
Deep Neural Network (DNN) classifiers are vulnerable to adversarial atta...
For visual-semantic embedding, the existing methods normally treat the
r...
Research in human action recognition has accelerated significantly since...