We introduce modifications to state-of-the-art approaches to aggregating
local video descriptors by using attention mechanisms and function
approximations. Rather than using ensembles of existing architectures, we
provide an insight on creating new architectures. We demonstrate our solutions
in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level
video and audio descriptors. We obtain testing accuracy similar to the state of
the art, while meeting budget constraints, and touch upon strategies to improve
the state of the art. Model implementations are available in
this https URL

本研究旨在通过引入基于注意力机制和函数逼近的方法来改进局部视频描述符集成的现有方法，并提出了创建新体系结构的见解。在使用帧级视频和音频描述符的 'The 2nd YouTube-8M Video Understanding Challenge' 中展示了我们的解决方案。通过满足预算约束条件，我们获得了类似于现有技术的测试准确性，并探讨了改进现有技术的策略。模型实现可在此 https URL 中获得。

可学习的池化方法用于视频分类

Learnable Pooling Methods for Video Classification

This paper describes our solution for the video recognition task of the
Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd
place. Because the challenge provides pre-extracted visual and audio features
instead of the raw videos, we mainly investigate various temporal modeling
approaches to aggregate the frame-level features for multi-label video
recognition. Our system contains three major components: two-stream sequence
model, fast-forward sequence model and temporal residual neural networks.
Experiment results on the challenging Youtube-8M dataset demonstrate that our
proposed temporal modeling approaches can significantly improve existing
temporal modeling approaches in the large-scale video recognition tasks. To be
noted, our fast-forward LSTM with a depth of 7 layers achieves 82.75% in term
of GAP@20 on the Kaggle Public test set.

该论文介绍了我们的解决方案，用于 Google Cloud 和 YouTube-8M 视频理解挑战的视频识别任务，我们通过各种时间建模方法对帧级特征进行聚合以提高多标签视频识别的准确性，并在 Kaggle 的公共测试集上取得了 82.75% 的性能提升。