This paper describes an attention-driven approach to 3-D point cloud sampling. We
establish our method based on a structure-aware attention discriminant analysis that …

Point cloud sampling is crucial for efficient large-scale point cloud analysis, where learning-
to-sample methods have recently received increasing attention from the community for …

Recently many approaches directly operate on point clouds for different tasks. These
approaches become more computation and storage demanding when point cloud size is …

We develop a phase-resolved wave field reconstruction method by the learning-based
downsampling network for processing large amounts of inhomogeneous data from non …

While point-based neural architectures have demonstrated their efficacy, the time-
consuming sampler currently prevents them from performing real-time reasoning on scene …

This vision paper proposes KGNet, an on-demand graph machine learning (GML) as a
service on top of RDF engines to support GML-enabled SPARQL queries. KGNet automates …

Due to the disorder of points, point clouds need to be structured by sampling and neighbor
query before feeding to Deep Neural Networks (DNNs). Structuring point clouds costs high …

Millimeter-wave (mmWave) radars have emerged as a promising technology for sensing
humans in diverse environments, owing to their ability to easily obtain 3D information in the …

Sampling is widely used in various point cloud tasks as it can effectively reduce resource
consumption. Recently, some methods have proposed utilizing neural networks to optimize …

In computer vision, long-tailed multi-label visual recognition is a challenging problem due to
the imbalance between classes and the recognition of rare classes. Previous methods for …