We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time. In this paper, we present an extensive analysis and solution to the underlying machine-learning problem based on frame-level data, where major challenges are identified and corresponding preliminary methods are proposed. It's noteworthy that, with merely the proposed strategies and uniformly-averaging multi-crop ensemble was it sufficient for us to reach our ranking. We also report the methods we believe to be promising but didn't have enough time to train to convergence. We hope this paper could serve, to some extent, as a review and guideline of the YouTube-8M multi-label video classification benchmark, inspiring future attempts and research.
@article{arxiv.1706.09274,
title = {The YouTube-8M Kaggle Competition: Challenges and Methods},
author = {Haosheng Zou and Kun Xu and Jialian Li and Jun Zhu},
journal= {arXiv preprint arXiv:1706.09274},
year = {2017}
}
Comments
accepted to CVPR'17 Workshop on YouTube-8M Large-Scale Video Understanding (oral presentation); code is at https://github.com/taufikxu/youtube on branches kunxu and zhs