FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 22106-22117
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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62206153,62125603)
This publication has 73 references indexed in Scilit:
- Speech-to-Gesture Generation2017
- Learning to Score Olympic Events2017
- Unite the People: Closing the Loop Between 3D and 2D Human Representations2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- The KIT Motion-Language DatasetBig Data, 2016
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- Panoptic Studio: A Massively Multiview System for Social Motion Capture2015
- SMPLACM Transactions on Graphics, 2015
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009