The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Point cloud data have been widely explored due to its superior accuracy and robustness
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …

As a promising scheme of self-supervised learning, masked autoencoding has significantly
advanced natural language processing and computer vision. Inspired by this, we propose a …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for
language and 2D image transformers. However, it still remains an open question on how to …

Pre-training by numerous image data has become de-facto for robust 2D representations. In
contrast, due to the expensive data processing, a paucity of 3D datasets severely hinders …

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object
classification, segmentation and detection is often laborious owing to the irregular structure …

Abstract 3D vision-language grounding (3D-VL) is an emerging field that aims to connect the
3D physical world with natural language, which is crucial for achieving embodied …

Recent advances in 3D semantic segmentation with deep neural networks have shown
remarkable success, with rapid performance increase on available datasets. However …

Existing approaches for unsupervised point cloud pre-training are constrained to either
scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose …