Human Action Recognition and Prediction: A Survey

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.

Cited by in corpus (9)

• A Review on Deep Learning Techniques for Video Prediction
• Levels of explainable artificial intelligence for human-aligned conversational explanations
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• Forecasting Action through Contact Representations from First Person Video
• Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction
• Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model
• Volterra Neural Networks (VNNs)
• Action Class Relation Detection and Classification Across Multiple Video Datasets
• From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks