Group-Skeleton-Based Human Action Recognition in Complex Events

by   Tingtian Li, et al.

Human action recognition as an important application of computer vision has been studied for decades. Among various approaches, skeleton-based methods recently attract increasing attention due to their robust and superior performance. However, existing skeleton-based methods ignore the potential action relationships between different persons, while the action of a person is highly likely to be impacted by another person especially in complex events. In this paper, we propose a novel group-skeleton-based human action recognition method in complex events. This method first utilizes multi-scale spatial-temporal graph convolutional networks (MS-G3Ds) to extract skeleton features from multiple persons. In addition to the traditional key point coordinates, we also input the key point speed values to the networks for better performance. Then we use multilayer perceptrons (MLPs) to embed the distance values between the reference person and other persons into the extracted features. Lastly, all the features are fed into another MS-G3D for feature fusion and classification. For avoiding class imbalance problems, the networks are trained with a focal loss. The proposed algorithm is also our solution for the Large-scale Human-centric Video Analysis in Complex Events Challenge. Results on the HiEve dataset show that our method can give superior performance compared to other state-of-the-art methods.


page 1

page 2

page 3

page 4


Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features

Recently skeleton-based action recognition has made signif-icant progres...

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

One-shot skeleton action recognition, which aims to learn a skeleton act...

Multi Scale Temporal Graph Networks For Skeleton-based Action Recognition

Graph convolutional networks (GCNs) can effectively capture the features...

Semantic Labeling of Human Action For Visually Impaired And Blind People Scene Interaction

The aim of this work is to contribute to the development of a tactile de...

Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment

Recognition of human actions and associated interactions with objects an...

Topology-aware MLP for Skeleton-based Action Recognition

Graph convolution networks (GCNs) have achieved remarkable performance i...

View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition

Skeleton-based human action recognition has recently attracted increasin...

Please sign up or login with your details

Forgot password? Click here to reset