arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.04555cs.CV
收藏

大规模Youtube-8 M视频理解的时间建模方法

Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding

Baidu IDL(百度深度学习实验室);Tsinghua University(清华大学)

Fu Li, Chuang Gan, Xiao Liu, Yunlong Bian, Xiang Long, Yandong Li, Zhichao Li, Jie Zhou, Shilei Wen

摘要:

本文介绍了我们的解决方案的视频识别任务的谷歌云和YouTube-8 M视频理解挑战赛,排名第三位。由于挑战提供了预提取的视觉和音频特征,而不是原始视频,我们主要研究各种时间建模方法来聚合多标签视频识别的帧级特征。我们的系统包含三个主要部分:双流序列模型,快进序列模型和时间残差神经网络。在具有挑战性的Youtube-8 M数据集上的实验结果表明,我们提出的时间建模方法可以显着改善现有的时间建模方法在大规模视频识别任务。值得注意的是,我们的7层快进LSTM在Kaggle公共测试集上的GAP@20达到了82.75%。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑