Multi-frame depth estimation generally achieves high accuracy relying on...
The standard approaches to neural network implementation yield powerful
...
This paper reviews the challenge on constrained high dynamic range (HDR)...
Continual Learning (CL) methods aim to enable machine learning models to...
A novel coronavirus disease 2019 (COVID-19) was detected and has spread
...
Unsupervised cross-domain person re-identification (Re-ID) aims to adapt...
Self-supervised learning (SlfSL), aiming at learning feature representat...
Most learning-based super-resolution (SR) methods aim to recover
high-re...
3D point cloud semantic and instance segmentation is crucial and fundame...
Vehicle re-identification (Re-ID) often requires one to recognize the
fi...
Training a semantic segmentation model requires a large amount of pixel-...
Removing rain effects from an image automatically has many applications ...
Ghosting artifacts caused by moving objects or misalignments is a key
ch...
Deep autoencoder has been extensively used for anomaly detection. Traini...
Both accuracy and efficiency are of significant importance to the task o...
RGB images differentiate from depth images as they carry more details ab...
Variational dropout (VD) is a generalization of Gaussian dropout, which ...
Cardiac magnetic resonance (CMR) is used extensively in the diagnosis an...
Total variation (TV) regularization has proven effective for a range of
...
As an integral component of blind image deblurring, non-blind deconvolut...
Removing pixel-wise heterogeneous motion blur is challenging due to the
...