Human Action Recognition and Prediction: A Survey

By Yu Kong, Yun Raymond Fu. International Journal of Computer Vision, 2018

806 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/025a44bf059aef8b9ee2e6ca598bebefc59a4a61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Review on Deep Learning Techniques for Video Prediction (2020, background): “tation [16], human action recognition and prediction [17], object pose estimation [18] and registration [19] to name a few, motivated authors to explore deep representationlearning models for future video frame prediction.”
A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms (2023, background): “Human action recognition is a vision-based technique that can identify a complete action performed by a human in a video sequence (Kong & Fu, 2022).”
SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments (2021, background): “The notion of drawing inspiration from conventional concepts in neuroscience and psychology to understand human perception of physical dynamics and causal reasoning has been around for some time [1, 5, 16, 19].”
Human Action Recognition From Various Data Modalities: A Review (2020, background): “[24] gave a survey about action recognition and prediction tasks.”
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding (2023, background): “, video question answering [37, 38], video captioning [34, 98], and human action recognition [36, 62, 63]).”
Coherent Temporal Synthesis for Incremental Action Segmentation (2024, neutral): “Action recognition [23], as the hallmark task of video understanding, was the initial focus for incremental learning for videos [3, 36, 37, 50].”
Predicting the Future from First Person (Egocentric) Vision: A Survey (2021, background): “For example, eye gaze and its role in security applications is analysed in [20], whereas multiple methods for action recognition and anticipation are listed in [21].”