SOTAVerified

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

2018-01-23Code Available1· sign in to hype

Sijie Yan, Yuanjun Xiong, Dahua Lin

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

Tasks

3D Human Pose EstimationAction RecognitionMultimodal Activity RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
H2O (2 Hands and Objects)ST-GCNActions Top-173.86—Unverified
ICVL-4ST-GCNAccuracy80.23—Unverified
IRDST-GCNAccuracy74.03—Unverified

Reproductions