Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives

TL;DR

This comprehensive review covers the progress, challenges, and future directions in group activity recognition in computer vision, emphasizing hierarchical modeling, relational architectures, and recent deep learning approaches.

Contribution

It provides an extensive overview of traditional and modern methods, including relational networks and attention mechanisms, highlighting recent advancements and future research directions.

Findings

Comparison of various recognition methods and their performance

Identification of key challenges in the field

Emerging perspectives for future research

Abstract

Group activity recognition is a hot topic in computer vision. Recognizing activities through group relationships plays a vital role in group activity recognition. It holds practical implications in various scenarios, such as video analysis, surveillance, automatic driving, and understanding social activities. The model's key capabilities encompass efficiently modeling hierarchical relationships within a scene and accurately extracting distinctive spatiotemporal features from groups. Given this technology's extensive applicability, identifying group activities has garnered significant research attention. This work examines the current progress in technology for recognizing group activities, with a specific focus on global interactivity and activities. Firstly, we comprehensively review the pertinent literature and various group activity recognition approaches, from traditional methodologies to the latest methods based on spatial structure, descriptors, non-deep learning, hierarchical recurrent neural networks (HRNN), relationship models, and attention mechanisms. Subsequently, we present the relational network and relational architectures for each module. Thirdly, we investigate methods for recognizing group activity and compare their performance with state-of-the-art technologies. We summarize the existing challenges and provide comprehensive guidance for newcomers to understand group activity recognition. Furthermore, we review emerging perspectives in group activity recognition to explore new directions and possibilities.