Panoramic Human Activity Recognition
This addresses the practical challenge of multi-granularity activity recognition in crowded scenes for applications like surveillance or social analysis, but it is incremental as it builds on existing graph neural network methods.
The paper tackles the problem of comprehensive activity understanding in crowded scenes by proposing panoramic human activity recognition (PAR) to simultaneously recognize individual actions, social group activities, and global activities, and develops a hierarchical graph neural network that shows effectiveness in experiments.
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.