Comparing Data Sources and Architectures for Deep Visual Representation Learning in Semantics

Comparing Data Sources and Architectures for Deep Visual Representation Learning in Semantics
复制标题

比较语义中深度视觉表示学习的数据源和架构

DOI:
10.18653/v1/d16-1043
复制
发表时间:
2016
期刊:
Artif. Intell.
影响因子:
--
通讯作者:
S. Clark
S. Clark
中科院分区:
--
文献类型:
--
作者:
Douwe Kiela;A. Vero;S. Clark

文献摘要

参考文献

被引文献

相似文献

多模态分布模型学习接地表示,以提高语义性能。使用卷积神经网络学习的深度视觉表示已被证明可以实现特别高的性能。在这项研究中,我们系统地比较了深度视觉表征学习技术,并尝试了三种著名的网络架构。此外,我们还探索了可用于检索相关图像的各种数据源,表明来自搜索引擎的图像与来自ImageNet等手动制作的资源的图像表现一样好,甚至更好。此外,我们探讨了最佳的图像数量和多模态语义的多语言适用性。我们希望这些发现可以作为该领域未来研究的指导。
Multi-modal distributional models learn grounded representations for improved performance in semantics. Deep visual representations, learned using convolutional neural networks, have been shown to achieve particularly high performance. In this study, we systematically compare deep visual representation learning techniques, experimenting with three well-known network architectures. In addition, we explore the various data sources that can be used for retrieving relevant images, showing that images from search engines perform as well as, or better than, those from manually crafted resources such as ImageNet. Furthermore, we explore the optimal number of images and the multi-lingual applicability of multi-modal semantics. We hope that these findings can serve as a guide for future research in the field.
利用图像通用性进行词汇蕴涵检测
DOI: --
发表时间: 2015
期刊: --
影响因子: --
作者:
Kiela, D.
通讯作者: Kiela, D.
DOI: 10.3115/v1/w14-1503
发表时间: 2014-04
期刊: --
影响因子: --
作者:
Douwe Kiela;S. Clark
通讯作者: Douwe Kiela;S. Clark