Group-Skeleton-Based Human Action Recognition in Complex Events

TL;DR

This paper introduces a novel group-skeleton-based human action recognition method that models interactions between multiple persons in complex events using multi-scale spatial-temporal graph convolutional networks and additional features like speed and distance.

Contribution

The paper proposes a new approach that incorporates inter-person relationships and additional features into skeleton-based action recognition, improving performance in complex event scenarios.

Findings

Achieved superior performance on the HiEve dataset.

Effectively models inter-person relationships in complex events.

Utilizes multi-scale spatial-temporal graph convolutional networks.

Abstract

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.