|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
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.
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-lifted
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
Point cloud is an important type of geometric data structure.
Ranked #2 on Scene Segmentation on ScanNet
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
Dynamics of human body skeletons convey significant information for human action recognition.
Ranked #2 on Multimodal Activity Recognition on EV-Action
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.
Ranked #2 on Action Recognition on UCF101
Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.
Ranked #4 on Sequential Image Classification on Sequential MNIST
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
Ranked #1 on Text Classification on Ohsumed