We introduce a method for flexible continual learning in open-vocabulary...
We investigate how to generate multimodal image outputs, such as RGB, de...
This paper aims for a new generation task: non-stationary multi-texture
...
In this paper, we aim to devise a universally versatile style transfer m...
Advanced face swapping methods have achieved appealing results. However,...
This paper proposes a new generative adversarial network for pose transf...
Face attribute editing aims to generate faces with one or multiple desir...
Visible watermarks are widely-used in images to protect copyright owners...
Learning-to-Rank (LTR) models trained from implicit feedback (e.g. click...
In this paper, we focus on semantically multi-modal image synthesis (SMI...
In this paper, we focus on semantically multi-modal image synthesis (SMI...
In this paper, we focus on effective methods for fast and accurate scene...
The non-local module works as a particularly useful technique for semant...
This paper proposes a new generative adversarial network for pose transf...
The real world exhibits an abundance of non-stationary textures. Example...
Text in natural images is of arbitrary orientations, requiring detection...
An important metric of users' satisfaction and engagement within on-line...
Object detection is an important and challenging problem in computer vis...
In this paper, we investigate the Chinese calligraphy synthesis problem:...
Person knowledge extraction is the foundation of the Tibetan knowledge g...