Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
Authors:
- Pingbo PanPPPingbo Pan
- Zhongwen XuZXZhongwen Xu
- Yi YangYYYi Yang
- Fei WuFWFei Wu
- Yueting ZhuangYZYueting Zhuang
Top Cited Papers
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1029-1038
Abstract
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 tran-sitions 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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion2015
- A dataset for Movie Description2015
- A discriminative CNN video representation for event detection2015
- Translating Videos to Natural Language Using Deep Recurrent Neural Networks2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Meteor Universal: Language Specific Translation Evaluation for Any Target Language2014
- Action Recognition with Improved Trajectories2013
- Image Classification with the Fisher Vector: Theory and PracticeInternational Journal of Computer Vision, 2013
- Video Google: a text retrieval approach to object matching in videos2003
- Long Short-Term MemoryNeural Computation, 1997