The unstructured nature of point clouds demands that local aggregation b...
Segmentation is an essential step for remote sensing image processing. T...
In the domain of remote sensing image interpretation, road extraction fr...
Parameter-efficient tuning aims to mitigate the large memory requirement...
Multi-task learning has proven to be effective in improving the performa...
Seeking legal advice is often expensive. Recent advancement in machine
l...
Neural Radiance Field (NeRF), a new novel view synthesis with implicit s...
Transformers have resulted in remarkable achievements in the field of im...
Snow is one of the toughest adverse weather conditions for object detect...
In recent years, Transformer models have been proven to have the remarka...
Although accurate and fast point cloud classification is a fundamental t...
Learning dense point-wise semantics from unstructured 3D point clouds wi...
We present a novel direction-aware feature-level frequency decomposition...
Building footprints data is of importance in several urban applications ...
Recently, methods based on Convolutional Neural Networks (CNN) achieved
...
This paper presents a Convolutional Neural Network (CNN) approach for
co...
Deep learning-based networks are among the most prominent methods to lea...
Ground filtering has remained a widely studied but incompletely resolved...
Deep Neural Networks (DNNs) learn representation from data with an impre...
In this paper, we propose a novel deep learning method based on a
Convol...
Stack interchanges are essential components of transportation systems. M...
Efficient inference for wide output layers (WOLs) is an essential yet
ch...
Recently, the advancement of deep learning in discriminative feature lea...
Semantic segmentation of large-scale outdoor point clouds is essential f...
As one of the most destructive disasters in the world, earthquake causes...
Recently there has been a flurry of interest around using pipeline
paral...
Squeeze-and-excitation (SE) module enhances the representational power o...
Middle-echo, which covers one or a few corresponding points, is a specif...
This paper proposes a new end-to-end trainable matching network based on...
Man-made environments typically comprise planar structures that exhibit
...
In this paper, we address the hyperspectral image (HSI) classification t...
We present a novel deep convolutional network pipeline, LO-Net, for real...
It is widely recognized that the deeper networks or networks with more
f...
This paper deals with the geometric multi-model fitting from noisy,
unst...
High spectral dimensionality and the shortage of annotations make
hypers...
The timely provision of traffic sign information to drivers is essential...
Geometric model fitting is a fundamental task in computer graphics and
c...
In this paper, we propose an effective scene text recognition method usi...