Graph convolutional networks: a comprehensive review
Graphs naturally appear in numerous application domains, ranging from social analysis,
bioinformatics to computer vision. The unique capability of graphs enables capturing the …
bioinformatics to computer vision. The unique capability of graphs enables capturing the …
Graph convolutional networks for computational drug development and discovery
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 …
over the past decade, its application in molecular informatics and drug discovery is still …
An end-to-end transformer model for 3d object detection
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 …
clouds. Compared to existing detection methods that employ a number of 3D-specific …
Pointcontrast: Unsupervised pre-training for 3d point cloud understanding
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 …
pre-training a network on a rich source set (eg, ImageNet) can help boost performance once …
Spatio-temporal self-supervised representation learning for 3d point clouds
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 …
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …
Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose
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 …
regress the pose and shape parameters of human mesh models, such as SMPL and MANO …
Measuring and relieving the over-smoothing problem for graph neural networks from the topological view
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 …
range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over …
Adaptive graph convolution for point cloud analysis
Convolution on 3D point clouds that generalized from 2D grid-like domains is widely
researched yet far from perfect. The standard convolution characterises feature …
researched yet far from perfect. The standard convolution characterises feature …
Kpconv: Flexible and deformable convolution for point clouds
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 …
ie that operates on point clouds without any intermediate representation. The convolution …
Graph attention convolution for point cloud semantic segmentation
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 …
isotropy about features. It neglects the structure of an object, results in poor object …