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 1511.03476cs.CV
收藏

分层递归神经网络视频编码器及其在字幕中的应用

Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning

University of Technology Sydney(悉尼科技大学);Zhejiang University(浙江大学)

Pingbo Pan, Zhongwen Xu, Yi Yang, Fei Wu, Yueting Zhuang

摘要:

最近,深度学习方法,特别是深度卷积神经网络(ConvNets),已经实现了图像分类的快速处理速度和压倒性的准确性。用深度ConvNets描述视频的时间结构成为视频内容分析的一个基本问题。在本文中,我们提出了一种新的方法,即层次递归神经编码器(HRNE),利用视频的时间信息。与目前的视频表示推理方法相比,本文做出了以下三个贡献。首先,我们的HRNE是能够有效地利用视频的时间结构在更长的范围内,通过减少输入信息流的长度,并在更高的水平上合成多个连续的输入。其次,计算操作显著减少,同时获得更多的非线性。第三,HRNE能够揭示具有不同粒度的帧块之间的时间转换,即,它可以对帧之间的时间转换以及段之间的转换进行建模。我们将新的方法应用到时间信息起着至关重要的作用的视频描述。实验表明,我们的方法优于国家的最先进的视频描述基准。值得注意的是,即使使用仅RGB流作为输入的单个网络,HRNE也击败了所有结合多个输入的最新系统,例如RGB ConvNet和3D ConvNet。

英文摘要:

Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for video representation becomes a fundamental problem for video content analysis. In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos. Compared to recent video representation inference approaches, this paper makes the following three contributions. First, our HRNE is able to efficiently exploit video temporal structure in a longer range by reducing the length of input information flow, and compositing multiple consecutive inputs at a higher level. Second, computation operations are significantly lessened while attaining more non-linearity. Third, HRNE is able to uncover temporal transitions between frame chunks with different granularities, i.e., it can model the temporal transitions between frames as well as the transitions between segments. We apply the new method to video captioning where temporal information plays a crucial role. Experiments demonstrate that our method outperforms the state-of-the-art on video captioning benchmarks. Notably, even using a single network with only RGB stream as input, HRNE beats all the recent systems which combine multiple inputs, such as RGB ConvNet plus 3D ConvNet.

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。

↑