arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.04569cs.CV
收藏

图像特异性

Image Specificity

Aalto University(阿尔托大学);Virginia Tech(弗吉尼亚理工学院暨州立大学)

Mainak Jas, Devi Parikh

摘要:

对于某些图像,多人撰写的描述彼此一致。但对于其他图像,不同人的描述差异很大。换句话说,一些图像是特定的$-$,它们从不同的人$-$引出一致的描述,而其他图像是模糊的。涉及图像和文本的应用程序可以从理解哪些图像是特定的,哪些图像是模糊的中受益。例如,考虑基于文本的图像检索。如果查询描述与模糊图像的标题(或参考描述)适度相似,则该查询可以被认为是与图像的适当匹配。但是,如果图像是非常具体的,查询和参考描述之间的适度相似性可能不足以检索图像。在本文中,我们介绍了图像特异性的概念。我们提出了两种机制来衡量特异性的图像的多个描述:一个自动化的措施和措施,依赖于人类的判断。我们根据图像内容和属性分析图像特异性,以更好地理解是什么使图像特异性。然后,我们训练模型来自动预测图像的特异性,而不需要图像的文本描述。最后,我们表明,建模图像特异性导致改进基于文本的图像检索应用程序。

英文摘要:

For some images, descriptions written by multiple people are consistent with each other. But for other images, descriptions across people vary considerably. In other words, some images are specific $-$ they elicit consistent descriptions from different people $-$ while other images are ambiguous. Applications involving images and text can benefit from an understanding of which images are specific and which ones are ambiguous. For instance, consider text-based image retrieval. If a query description is moderately similar to the caption (or reference description) of an ambiguous image, that query may be considered a decent match to the image. But if the image is very specific, a moderate similarity between the query and the reference description may not be sufficient to retrieve the image. In this paper, we introduce the notion of image specificity. We present two mechanisms to measure specificity given multiple descriptions of an image: an automated measure and a measure that relies on human judgement. We analyze image specificity with respect to image content and properties to better understand what makes an image specific. We then train models to automatically predict the specificity of an image from image features alone without requiring textual descriptions of the image. Finally, we show that modeling image specificity leads to improvements in a text-based image retrieval application.

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。

↑