Recent Progress in Appearance-based Action Recognition

TL;DR

This paper reviews recent advancements in appearance-based action recognition, categorizing methods into four groups, analyzing their effectiveness, and highlighting future research directions in the field.

Contribution

It provides a comprehensive categorization and analysis of recent appearance-based action recognition methods, summarizing empirical results and identifying key future research areas.

Findings

2D convolutional methods show strong spatial feature modeling.

3D convolutional methods improve temporal understanding.

Motion and context-based methods enhance recognition accuracy.

Abstract

Action recognition, which is formulated as a task to identify various human actions in a video, has attracted increasing interest from computer vision researchers due to its importance in various applications. Recently, appearance-based methods have achieved promising progress towards accurate action recognition. In general, these methods mainly fulfill the task by applying various schemes to model spatial and temporal visual information effectively. To better understand the current progress of appearance-based action recognition, we provide a comprehensive review of recent achievements in this area. In particular, we summarise and discuss several dozens of related research papers, which can be roughly divided into four categories according to different appearance modelling strategies. The obtained categories include 2D convolutional methods, 3D convolutional methods, motion representation-based methods, and context representation-based methods. We analyse and discuss representative methods from each category, comprehensively. Empirical results are also summarised to better illustrate cutting-edge algorithms. We conclude by identifying important areas for future research gleaned from our categorisation.