Attention-based graph neural networks have made great progress in featur...
Accurately matching local features between a pair of images is a challen...
Image deblurring continues to achieve impressive performance with the
de...
Color plays an important role in human visual perception, reflecting the...
Deep-learning-based local feature extraction algorithms that combine
det...
As far as Scene Graph Generation (SGG), coarse and fine predicates mix i...
To solve the ill-posed problem of hyperspectral image super-resolution
(...
Recently, face super-resolution (FSR) methods either feed whole face ima...
High-resolution (HR) hyperspectral face image plays an important role in...
Recently, the problem of inaccurate learning targets in crowd counting d...
Modifications on triplet loss that rescale the back-propagated gradients...
The defocus deblurring raised from the finite aperture size and exposure...
Most existing deep learning-based pan-sharpening methods have several wi...
Most recent video super-resolution (SR) methods either adopt an iterativ...
Face super-resolution, also known as face hallucination, which is aimed ...
We present a framework for robust electric network frequency (ENF) extra...
Recently, single gray/RGB image super-resolution reconstruction task has...
We propose to incorporate neural architecture search (NAS) into
general-...
It is challenging to inpaint face images in the wild, due to the large
v...
Image-to-image translation is to convert an image of the certain style t...
By developing sophisticated image priors or designing deep(er) architect...
Being accurate, efficient, and compact is essential to a facial landmark...
Label information plays an important role in supervised hyperspectral im...
Face hallucination is a technique that reconstruct high-resolution (HR) ...
Most of the current face hallucination methods, whether they are shallow...
As an unsupervised dimensionality reduction method, principal component
...
State-of-the-art Convolutional Neural Network (CNN) benefits a lot from
...
This paper addresses the problem of face recognition when there is only ...
Region search is widely used for object localization. Typically, the reg...