CVNov 26, 2020

Group-Skeleton-Based Human Action Recognition in Complex Events

arXiv:2011.13273v27 citations
AI Analysis

This work provides an incremental improvement for human action recognition in complex multi-person scenarios, which is relevant for computer vision researchers and applications requiring understanding of group interactions.

This paper addresses human action recognition in complex events by proposing a group-skeleton-based method that considers inter-person action relationships. The method extracts multi-person skeleton features, incorporates key point speed, and embeds inter-person distance values, achieving superior performance on the HiEve dataset compared to state-of-the-art methods.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes