Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …

Neural fields excel in computer vision and robotics due to their ability to understand the 3D
visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of …

Contrastive learning has recently demonstrated great potential for unsupervised pre-training
in 3D scene understanding tasks. However, most existing work randomly selects point …

Abstract Text, 2D, and 3D information are crucial information representations in modern
science and management disciplines. However, complex and irregular 3D data produce …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in
many vision tasks. This calls for the 3D understanding directly in this representation space …

In this work, we survey recent studies on masked image modeling (MIM), an approach that
emerged as a powerful self-supervised learning technique in computer vision. The MIM task …

Human action recognition plays a pivotal role in various real-world applications, including
surveillance systems, robotics, and occupant monitoring in the car interior. With such a …

Deep neural networks (DNNs) have been widely used for mesh processing in recent years.
However, current DNNs can not process arbitrary meshes efficiently. On the one hand, most …