Graphs naturally appear in numerous application domains, ranging from social analysis,
bioinformatics to computer vision. The unique capability of graphs enables capturing the …

Despite the fact that deep learning has achieved remarkable success in various domains
over the past decade, its application in molecular informatics and drug discovery is still …

We propose 3DETR, an end-to-end Transformer based object detection model for 3D point
clouds. Compared to existing detection methods that employ a number of 3D-specific …

Arguably one of the top success stories of deep learning is transfer learning. The finding that
pre-training a network on a rich source set (eg, ImageNet) can help boost performance once …

To date, various 3D scene understanding tasks still lack practical and generalizable pre-
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …

Most of the recent deep learning-based 3D human pose and mesh estimation methods
regress the pose and shape parameters of human mesh models, such as SMPL and MANO …

Abstract Graph Neural Networks (GNNs) have achieved promising performance on a wide
range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over …

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely
researched yet far from perfect. The standard convolution characterises feature …

Abstract We present Kernel Point Convolution (KPConv), a new design of point convolution,
ie that operates on point clouds without any intermediate representation. The convolution …

Standard convolution is inherently limited for semantic segmentation of point cloud due to its
isotropy about features. It neglects the structure of an object, results in poor object …