ChaLearn Looking at People Challenge 2014: Dataset and Results
Abstract
This paper summarizes the ChaLearn Looking at People 2014 challenge data and the results obtained by the participants. The competition was split into three independent tracks: human pose recovery from RGB data, action and interaction recognition from RGB data sequences, and multi-modal gesture recognition from RGB-Depth sequences. For all the tracks, the goal was to perform user-independent recognition in sequences of continuous images using the overlapping Jaccard index as the evaluation measure. In this edition of the ChaLearn challenge, two large novel data sets were made publicly available and the Microsoft Codalab platform were used to manage the competition. Outstanding results were achieved in the three challenge tracks, with accuracy results of 0.20, 0.50, and 0.85 for pose recovery, action/interaction recognition, and multi-modal gesture recognition, respectively.
Cite
Text
Escalera et al. "ChaLearn Looking at People Challenge 2014: Dataset and Results." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16178-5_32Markdown
[Escalera et al. "ChaLearn Looking at People Challenge 2014: Dataset and Results." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/escalera2014eccvw-chalearn/) doi:10.1007/978-3-319-16178-5_32BibTeX
@inproceedings{escalera2014eccvw-chalearn,
title = {{ChaLearn Looking at People Challenge 2014: Dataset and Results}},
author = {Escalera, Sergio and Baró, Xavier and Gonzàlez, Jordi and Bautista, Miguel Ángel and Madadi, Meysam and Reyes, Miguel and Ponce-López, Víctor and Escalante, Hugo Jair and Shotton, Jamie and Guyon, Isabelle},
booktitle = {European Conference on Computer Vision Workshops},
year = {2014},
pages = {459-473},
doi = {10.1007/978-3-319-16178-5_32},
url = {https://mlanthology.org/eccvw/2014/escalera2014eccvw-chalearn/}
}