arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.03671cs.CL
收藏

基于短语的图像描述

Phrase-based Image Captioning

Idiap Research Institute(Idiap研究所);École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院(EPFL));Facebook AI Research(Facebook人工智能研究院)

Rémi Lebret, Pedro O. Pinheiro, Ronan Collobert

摘要:

生成图像的新颖文本描述是连接计算机视觉和自然语言处理的有趣问题。在本文中,我们提出了一个简单的模型,能够生成描述性的句子给定的样本图像。这个模型非常注重描述的语法。我们训练一个纯双线性模型,该模型学习图像表示(从先前训练的卷积神经网络生成)和用于描述它们的短语之间的度量。然后,系统能够从给定的图像样本中推断短语。基于字幕语法统计,我们提出了一个简单的语言模型,可以产生相关的描述一个给定的测试图像使用的短语推断。我们的方法比最先进的模型要简单得多,在两个流行的数据集Flickr30k和最近提出的Microsoft COCO中取得了相当的结果。

英文摘要:

Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption syntax statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results in two popular datasets for the task: Flickr30k and the recently proposed Microsoft COCO.

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。

↑