In this paper, we propose a novel cross-modal distillation method, calle...
Recent advances on text-to-image generation have witnessed the rise of
d...
Outlier detection tasks have been playing a critical role in AI safety. ...
BERT-type structure has led to the revolution of vision-language pre-tra...
Localizing text instances in natural scenes is regarded as a fundamental...
Vision Transformer has shown great visual representation power in substa...
We present a new perspective of achieving image synthesis by viewing thi...
The defect detection task can be regarded as a realistic scenario of obj...
Unsupervised learning is just at a tipping point where it could really t...
Relative position encoding (RPE) is important for transformer to capture...
Reshaping accurate and realistic 3D human bodies from anthropometric
par...
State-of-the-art image inpainting approaches can suffer from generating
...
High-quality video inpainting that completes missing regions in video fr...
Automatically standardizing nomenclature for anatomical structures in
ra...
In this paper, we propose a simple yet effective method to endow deep 3D...
We study on weakly-supervised object detection (WSOD) which plays a vita...
The problem of distance metric learning is mostly considered from the
pe...
Deep models are capable of fitting complex high dimensional functions wh...
It is well believed that video captioning is a fundamental but challengi...
Image captioning has received significant attention with remarkable
impr...
High-quality image inpainting requires filling missing regions in a dama...
Previous works have shown that face recognition with high accuracy 3D da...
Automatically describing a video with natural language is regarded as a
...
Training data are critical in face recognition systems. However, labelin...
Deep models have achieved impressive performance for face hallucination
...
We consider the compression artifacts reduction problem, where a compres...
Bezigons, i.e., closed paths composed of Bézier curves, have been widely...
Identifying the same individual across different scenes is an important ...