3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition

TL;DR

This paper explores the use of 3D convolutional networks for classifying continuous sports videos, specifically focusing on actions like table tennis strokes, demonstrating their effectiveness in complex, real-world environments.

Contribution

It applies 3D convolutional networks to continuous, ecological sports videos for action recognition, highlighting their utility in challenging segmentation and classification tasks.

Findings

Effective segmentation and classification of sports actions

3D convnets handle ecological environment videos well

Window-based approaches improve recognition accuracy

Abstract

3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification of continuous video takes with repeatable actions, such as strokes of table tennis. Filmed in a free marker less ecological environment, these videos represent a challenge from both segmentation and classification point of view. The 3D convnets are an efficient tool for solving these problems with window-based approaches.