arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.12401cs.CVcs.CLcs.LGstat.ML
收藏

一种基于图像描述的层次化视觉故事讲述方法

A Hierarchical Approach for Visual Storytelling Using Image Description

University of Kentucky(肯塔基大学)

Md Sultan Al Nahian, Tasmia Tasrin, Sagar Gandhi, Ryan Gaines, Brent Harrison

摘要:

视觉故事的主要挑战之一是开发能够在长事件序列中保持故事背景的技术,以生成类似人类的故事。在本文中,我们提出了一种基于编码器-解码器网络的分层深度学习架构来解决这个问题。为了更好地帮助我们的网络在生成长而多样的句子的同时保持这种上下文,我们将自然语言图像描述与图像本身结合起来,以生成每个故事句子。我们在Visual Storytelling(VIST)数据集上评估了我们的系统,并表明我们的方法在一套不同的自动评估指标上优于最先进的技术。从这次评估的实证结果表明,我们提出的架构的不同组成部分的必要性,并显示了视觉讲故事的架构的有效性。

英文摘要:

One of the primary challenges of visual storytelling is developing techniques that can maintain the context of the story over long event sequences to generate human-like stories. In this paper, we propose a hierarchical deep learning architecture based on encoder-decoder networks to address this problem. To better help our network maintain this context while also generating long and diverse sentences, we incorporate natural language image descriptions along with the images themselves to generate each story sentence. We evaluate our system on the Visual Storytelling (VIST) dataset and show that our method outperforms state-of-the-art techniques on a suite of different automatic evaluation metrics. The empirical results from this evaluation demonstrate the necessities of different components of our proposed architecture and shows the effectiveness of the architecture for visual storytelling.

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。

↑