Abstract 3D dense captioning aims to generate multiple captions localized with their
associated object regions. Existing methods follow a sophisticated" detect-then-describe" …

In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

The point cloud feature aggregation, which learns discriminative features from the
disordered points, plays a key role for large-scale point cloud semantic segmentation. Most …

In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image
domain due to the less requirement for labeled training data and greater generalization for …

This paper investigates how to leverage more readily acquired annotations, ie, 3D bounding
boxes instead of dense point-wise labels, for instance segmentation. We propose a Weakly …

Weakly supervised 3D instance segmentation on point clouds has been rarely studied in
recent years. Due to the few annotated labels of 3D point clouds, how to learn discriminative …

To overcome the data hungry challenge, we have proposed a semi-supervised contrastive
learning framework for the task of class-imbalanced semantic segmentation. First and …

Point cloud segmentation is an essential task in three-dimensional (3D) vision and
intelligence. It is a critical step in understanding 3D scenes with a variety of applications …

Urban meshes semantic segmentation is essential for comprehending the 3D real-world
environments, as it plays a vital role across various application domains, including digital …

Instance segmentation is a crucial research task in the field of computer vision, providing an
indispensable theoretical foundation for the development of panoramic segmentation …