FLAG3D: A 3D Fitness Activity Dataset with Language Instruction

TL;DR

FLAG3D is a comprehensive large-scale 3D fitness activity dataset with detailed language instructions, enabling advancements in action recognition, human mesh recovery, and language-guided action generation in diverse environments.

Contribution

The paper introduces FLAG3D, a novel dataset with high-quality 3D human poses, detailed language annotations, and diverse natural environment videos for fitness activities.

Findings

Facilitates cross-domain human action recognition

Enables dynamic human mesh recovery research

Supports language-guided human action generation

Abstract

With the continuously thriving popularity around the world, fitness activity analytic has become an emerging research topic in computer vision. While a variety of new tasks and algorithms have been proposed recently, there are growing hunger for data resources involved in high-quality data, fine-grained labels, and diverse environments. In this paper, we present FLAG3D, a large-scale 3D fitness activity dataset with language instruction containing 180K sequences of 60 categories. FLAG3D features the following three aspects: 1) accurate and dense 3D human pose captured from advanced MoCap system to handle the complex activity and large movement, 2) detailed and professional language instruction to describe how to perform a specific activity, 3) versatile video resources from a high-tech MoCap system, rendering software, and cost-effective smartphones in natural environments. Extensive experiments and in-depth analysis show that FLAG3D contributes great research value for various challenges, such as cross-domain human action recognition, dynamic human mesh recovery, and language-guided human action generation. Our dataset and source code are publicly available at https://andytang15.github.io/FLAG3D.