Panoramic Human Activity Recognition

TL;DR

This paper introduces panoramic human activity recognition (PAR), a new comprehensive approach to simultaneously identify individual actions, social group activities, and global crowd behaviors using a hierarchical graph neural network, supported by a new benchmark.

Contribution

The paper proposes a novel hierarchical graph neural network for PAR and establishes a benchmark for evaluating this and related methods.

Findings

The proposed method effectively models multi-granularity activities and social relations.

Experimental results demonstrate the effectiveness of the PAR approach.

The benchmark provides a valuable resource for future research in this area.

Abstract

To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simultaneous achieve the individual action, social group activity, and global activity recognition. This is a challenging yet practical problem in real-world applications. For this problem, we develop a novel hierarchical graph neural network to progressively represent and model the multi-granularity human activities and mutual social relations for a crowd of people. We further build a benchmark to evaluate the proposed method and other existing related methods. Experimental results verify the rationality of the proposed PAR problem, the effectiveness of our method and the usefulness of the benchmark. We will release the source code and benchmark to the public for promoting the study on this problem.