This paper presents our 7th place solution to the second YouTube-8M video
understanding competition which challenges participates to build a
constrained-size model to classify millions of YouTube videos into thousands of
classes. Our final model consists of four single models aggregated into one
tensorflow graph. For each single model, we use the same network architecture
as in the winning solution of the first YouTube-8M video understanding
competition, namely Gated NetVLAD. We train the single models separately in
tensorflow's default float32 precision, then replace weights with float16
precision and ensemble them in the evaluation and inference stages., achieving
48.5% compression rate without loss of precision. Our best model achieved
88.324% GAP on private leaderboard. The code is publicly available at
this https URL

本文介绍了我们在第二届 YouTube-8M 视频理解竞赛中取得第七名的方案，该方案挑战参与者建立一个大小受限的模型来将数百万 YouTube 视频分类为数千个类别。我们的最终模型由四个单一的模型组成，并在评估和推断阶段集成它们，在不损失精度的情况下实现了 48.5％的压缩率，并在私人排行榜上取得了 88.324％的 GAP。