A Survey on Deep Learning Techniques for Action Anticipation

TL;DR

This survey reviews recent deep learning methods for action anticipation, focusing on daily-living scenarios, classification of approaches, evaluation metrics, datasets, and future research directions.

Contribution

It systematically classifies and summarizes recent deep learning techniques for action anticipation in daily-living contexts, providing a comprehensive overview.

Findings

Deep learning approaches dominate action anticipation research.

Common datasets and metrics are identified and discussed.

Future directions include addressing dataset limitations and improving model robustness.

Abstract

The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction. Consequently, numerous methods have been introduced for action anticipation in recent years, with deep learning-based approaches being particularly popular. In this work, we review the recent advances of action anticipation algorithms with a particular focus on daily-living scenarios. Additionally, we classify these methods according to their primary contributions and summarize them in tabular form, allowing readers to grasp the details at a glance. Furthermore, we delve into the common evaluation metrics and datasets used for action anticipation and provide future directions with systematical discussions.