Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
Preprint
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 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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Beyond short snippets: Deep networks for video classification2015
- Going deeper with convolutions2015
- CIDEr: Consensus-based image description evaluation2015
- A dataset for Movie Description2015
- A discriminative CNN video representation for event detection2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Microsoft COCO: Common Objects in Context2014
- Image Classification with the Fisher Vector: Theory and PracticeInternational Journal of Computer Vision, 2013
- Action recognition by dense trajectories2011
- Aggregating local descriptors into a compact image representation2010