Human Action Recognition and Prediction: A Survey

TL;DR

This survey reviews recent advances in vision-based human action recognition and prediction, highlighting models, datasets, challenges, and future research directions in this rapidly evolving field.

Contribution

It provides a comprehensive overview of state-of-the-art techniques, datasets, and evaluation protocols for human action recognition and prediction, emphasizing recent progress and challenges.

Findings

Summarizes key models and algorithms in action recognition and prediction.

Analyzes popular datasets and evaluation protocols.

Discusses future research directions and technical challenges.

Abstract

Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action recognition and prediction from videos are such tasks, where action recognition is to infer human actions (present state) based upon complete action executions, and action prediction to predict human actions (future state) based upon incomplete action executions. These two tasks have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as visual surveillance, autonomous driving vehicle, entertainment, and video retrieval, etc. Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction. In this paper, we survey the complete state-of-the-art techniques in action recognition and prediction. Existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions are also provided with systematic discussions.