Skeleton Based Action Recognition

83 papers with code • 29 benchmarks • 19 datasets

Greatest papers with code

Semi-Supervised Classification with Graph Convolutional Networks

tkipf/gcn 9 Sep 2016

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.

Document Classification General Classification +4

Graph Attention Networks

labmlai/annotated_deep_learning_paper_implementations ICLR 2018

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.

Document Classification Graph Attention +7

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

deepmind/kinetics-i3d CVPR 2017

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.

Action Recognition General Classification +1

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

mdeff/cnn_graph NeurIPS 2016

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.

Node Classification Skeleton Based Action Recognition

Revisiting Skeleton-based Action Recognition

open-mmlab/mmaction2 28 Apr 2021

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.

Action Recognition Pose Estimation +1

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

benedekrozemberczki/pytorch_geometric_temporal CVPR 2019

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.

Action Recognition graph construction +1