3D scene understanding has gained significant attention due to its wide ...
3D visual grounding aims to localize the target object in a 3D point clo...
3D visual grounding involves finding a target object in a 3D scene that
...
Multi-modal Contrastive Representation (MCR) learning aims to encode
dif...
Multi-media communications facilitate global interaction among people.
H...
Frame interpolation attempts to synthesise intermediate frames given one...
The most prominent problem associated with the deconvolution layer is th...
Convolutional neural networks have enabled accurate image super-resoluti...
In this note, we want to focus on aspects related to two questions most
...
Recently, several models based on deep neural networks have achieved gre...
Despite the breakthroughs in accuracy and speed of single image
super-re...