arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.09536cs.CV
收藏

从图像到语言理解:字幕法

Image to Language Understanding: Captioning approach

Columbia University(哥伦比亚大学)

Madhavan Seshadri, Malavika Srikanth, Mikhail Belov

摘要:

在计算机科学的发展中,从视觉表示中提取上下文是至关重要的。用自然语言表示这样的格式具有各种各样的应用,例如帮助视力受损者等。这样的方法是计算机视觉和自然语言技术的组合,这是一个很难解决的问题。这个项目的目的是比较不同的方法来解决图像描述的问题。具体而言,重点是比较两种不同类型的模型:编码器-解码器方法和多模型方法。在编码器-解码器方法中,将注入和合并架构与主要基于目标检测的多模态图像描述方法进行比较。这些方法是基于最先进的句子比较指标进行比较的,例如BLEU,GLEU,Meteor和Rouge,这些指标是在包含100 k图像的Google Conceptual captions数据集的子集上进行的。在此比较的基础上,我们观察到最好的模型是Inception注入编码器模型。这一最佳方法已作为一个基于网络的系统部署。在上传图像时,这样的系统将输出与图像相关联的最佳标题。

英文摘要:

Extracting context from visual representations is of utmost importance in the advancement of Computer Science. Representation of such a format in Natural Language has a huge variety of applications such as helping the visually impaired etc. Such an approach is a combination of Computer Vision and Natural Language techniques which is a hard problem to solve. This project aims to compare different approaches for solving the image captioning problem. In specific, the focus was on comparing two different types of models: Encoder-Decoder approach and a Multi-model approach. In the encoder-decoder approach, inject and merge architectures were compared against a multi-modal image captioning approach based primarily on object detection. These approaches have been compared on the basis on state of the art sentence comparison metrics such as BLEU, GLEU, Meteor, and Rouge on a subset of the Google Conceptual captions dataset which contains 100k images. On the basis of this comparison, we observed that the best model was the Inception injected encoder model. This best approach has been deployed as a web-based system. On uploading an image, such a system will output the best caption associated with the image.

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。

↑