Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

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 …

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training
(CLIP) have shown inspirational performance on 2D visual recognition, which learns to …

Abstract Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled
text-image pairs, has demonstrated great performance in open-world vision understanding …

Pre-training across 3D vision and language remains under development because of limited
training data. Recent works attempt to transfer vision-language (VL) pre-training methods to …

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

Large-scale pre-trained models have shown promising open-world performance for both
vision and language tasks. However, their transferred capacity on 3D point clouds is still …

Training a 3D scene understanding model requires complicated human annotations, which
are laborious to collect and result in a model only encoding close-set object semantics. In …

Zero-shot point cloud segmentation aims to make deep models capable of recognizing
novel objects in point cloud that are unseen in the training phase. Recent trends favor the …

Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes
to a well-trained base model in multiple training sessions with the restriction that only a few …