Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples
under the condition that some output classes are unknown during supervised learning. To …

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 …

Open-vocabulary scene understanding aims to localize and recognize unseen categories
beyond the annotated label space. The recent breakthrough of 2D open-vocabulary …

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

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 …

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts
gradually, where only a few examples per concept are available to the learner. Due to the …

We propose a lightweight and scalable Regional Point-Language Contrastive learning
framework namely RegionPLC for open-world 3D scene understanding aiming to identify …

In dynamic 3D environments the ability to recognize a diverse range of objects without the
constraints of predefined categories is indispensable for real-world applications. In response …

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 …

Point clouds consist of 3D data points and are among the most considerable data formats for
3D representations. Their popularity is due to their broad application areas, such as robotics …