Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning

TL;DR

The paper introduces HRNE, a hierarchical recurrent neural encoder that effectively captures long-range temporal dependencies in videos, improving video captioning performance with fewer computations and better modeling of temporal transitions.

Contribution

The paper presents HRNE, a novel hierarchical RNN architecture that efficiently models long-range temporal structure in videos for improved captioning.

Findings

HRNE outperforms state-of-the-art on video captioning benchmarks.

HRNE achieves better results using only RGB input compared to multi-input systems.

The method reduces computational complexity while capturing detailed temporal transitions.

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.