Research on Deep Learning-based Group Recognition

Abstract

The task of group recognition is a process of automatically recognizing and analyzing individuals or groups from a large population using computer vision and machine learning techniques. Currently, the main methods for group recognition using deep networks can be divided into four categories: methods based on convolutional neural networks (CNN), methods based on recurrent neural networks (RNN), combined CNN-RNN-based methods, as well as pose analysis methods. This article specifically analyzes these four categories of methods: CNN-based, RNN-based, and pose analysis, and summarizes the characteristics and functions of iterative deep learning models, graph convolutional network models, long short-term memory models, pose models, and skeleton models. In addition, a detailed introduction to commonly used datasets in group recognition is provided, and the main evaluation metrics are analyzed. Finally, important research directions in group recognition are discussed, followed by a conclusion of the entire article.