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.

本文介绍了我们参加 YouTube-8M 视频理解挑战的经历和成果，并提供了基于帧级数据的机器学习问题的深入分析和解决方案。我们通过统一平均的多剪辑集成方法，只使用提出的策略就实现了前十名的成绩，同时也介绍了一些有潜力但时间不足无法训练到收敛的方法。希望本文能起到对 YouTube-8M 多标签视频分类基准的一定回顾和指导作用，激发未来尝试和研究的灵感。