Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …

In many ways, graphs are the main modality of data we receive from nature. This is due to
the fact that most of the patterns we see, both in natural and artificial systems, are elegantly …

Structural pruning enables model acceleration by removing structurally-grouped parameters
from neural networks. However, the parameter-grou** patterns vary widely across …

Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

The recognition capabilities of current state-of-the-art 3D models are limited by datasets with
a small number of annotated data and a pre-defined set of categories. In its 2D counterpart …

PointNet++ is one of the most influential neural architectures for point cloud understanding.
Although the accuracy of PointNet++ has been largely surpassed by recent networks such …

As a pioneering work exploring transformer architecture for 3D point cloud understanding,
Point Transformer achieves impressive results on multiple highly competitive benchmarks. In …

Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF,
have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch …

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of
large-scale real-scanned 3D databases. To facilitate the development of 3D perception …

Network architecture plays a key role in the deep learning-based computer vision system.
The widely-used convolutional neural network and transformer treat the image as a grid or …