83 papers with code • 29 benchmarks • 19 datasets
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.
Ranked #1 on Graph Classification on IPC-grounded
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
Ranked #2 on Node Classification on Wiki-Vote
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks.
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs.
Ranked #4 on Skeleton Based Action Recognition on SBU
In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
Ranked #1 on Skeleton Based Action Recognition on Kinetics-Skeleton dataset (using extra training data)
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #3 on Skeleton Based Action Recognition on UAV-Human