CNNs and Transformers have their own advantages and both have been widel...
How to enable learnability for new classes while keeping the capability ...
Optimizer is an essential component for the success of deep learning, wh...
Referring video object segmentation (RVOS) aims to segment the target ob...
Image restoration aims to reconstruct degraded images, e.g., denoising o...
Universal Information Extraction (UIE) has been introduced as a unified
...
Diffusion models have recently received a surge of interest due to their...
Masked Image Modeling (MIM) is a new self-supervised vision pre-training...
Convolution neural networks (CNNs) and Transformers have their own advan...
In order to get raw images of high quality for downstream Image Signal
P...
Road segmentation from remote sensing images is a challenging task with ...
Unsupervised domain adaptation (UDA) for semantic segmentation aims to a...
As the COVID-19 epidemic began to worsen in the first months of 2020,
st...
In neural networks, developing regularization algorithms to settle
overf...
Existing inpainting methods have achieved promising performance for
reco...
Convolutional Neural Network (CNN) has demonstrated impressive ability t...
Multi-label learning draws great interests in many real world applicatio...
How can we find a general way to choose the most suitable samples for
tr...
In hyperspectral remote sensing data mining, it is important to take int...
Recently, deep learning based video super-resolution (SR) methods have
a...
With the wide applications of Unmanned Aerial Vehicle (UAV) in engineeri...
Domain adaptation refers to the process of learning prediction models in...
We study the problem of unsupervised domain adaptive re-identification
(...
One of the main purposes of earth observation is to extract interested
i...