首页> 外文会议>5th workshop on vision and language >Detecting Visually Relevant Sentences for Fine-Grained Classification
【24h】

Detecting Visually Relevant Sentences for Fine-Grained Classification

机译:检测视觉相关句子以进行细粒度分类

获取原文
获取原文并翻译 | 示例

摘要

Detecting discriminative semantic attributes from text which correlate with image features is one of the main challenges of zero-shot learning for fine-grained image classification. Particularly, using full-length encyclopedic articles as textual descriptions has had limited success, one reason being that such documents contain many non-visual or unrelated sentences. We propose a method to automatically extract visually relevant sentences from Wikipedia documents. Our model, based on a convolutional neural network, is robustly tested through ground truth labeling obtained via Amazon Mechanical Turk, achieving 81.73% F1 measure.
机译:从文本中识别与图像特征相关的区别性语义属性是零射击学习对精细图像分类的主要挑战之一。特别地,使用全长百科全书文章作为文本描述具有有限的成功,原因之一是这种文档包含许多非视觉或无关的句子。我们提出了一种从Wikipedia文档中自动提取视觉相关句子的方法。我们的模型基于卷积神经网络,通过通过Amazon Mechanical Turk获得的地面真相标签进行了稳健的测试,实现了81.73%的F1测度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号