Vision-language models have recently shown great potential on many compu...
In computer vision, fine-tuning is the de-facto approach to leverage
pre...
Exploiting convolutional neural networks for point cloud processing is q...
Previous methods for skeleton-based gesture recognition mostly arrange t...
In recent years, deep learning methods bring incredible progress to the ...
Numerical Weather Prediction (NWP), is widely used in precipitation
fore...
Current state-of-the-art detectors typically exploit feature pyramid to
...
Chinese character synthesis involves two related aspects, i.e., style
ma...
Point cloud processing is very challenging, as the diverse shapes formed...
For network architecture search (NAS), it is crucial but challenging to
...
Traditional clustering methods often perform clustering with low-level
i...
Face detection, as a fundamental technology for various applications, is...
Point cloud analysis is very challenging, as the shape implied in irregu...
Object detectors are usually equipped with networks designed for image
c...
Transferring image-based object detectors to domain of videos remains a
...
Designing neural architectures is a fundamental step in deep learning
ap...
Multi-label image classification is a fundamental but challenging task
t...
Semantic labeling for very high resolution (VHR) images in urban areas, ...
This paper performs a comprehensive and comparative evaluation of the st...
Binary features have been incrementally popular in the past few years du...
Subset selection from massive data with noised information is increasing...
Hyperspectral unmixing (HU) plays a fundamental role in a wide range of
...
Hyperspectral Unmixing (HU) has received increasing attention in the pas...
Hyperspectral unmixing is one of the crucial steps for many hyperspectra...