• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering >Topic-Based Image Caption Generation
【24h】

Topic-Based Image Caption Generation

机译：基于主题的图像标题生成

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image captioning is to generate captions for a given image based on the content of the image. To describe an image efficiently,it requires extracting as much information from it as possible. Apart from detecting the presence of objects and their relativeorientation, the respective purpose intending the topic of the image is another vital information which can be incorporatedwith the model to improve the efficiency of the caption generation system. The sole aim is to put extra thrust on the contextof the image imitating human approach, as the mere presence of objects which may not be related to the context representingthe image should not be a part of the generated caption. In this work, the focus is on detecting the topic concerning the imageso as to guide a novel deep learning-based encoder–decoder framework to generate captions for the image. The method iscompared with some of the earlier state-of-the-art models based on the result obtained from MSCOCO 2017 training dataset. BLEU, CIDEr, ROGUE-L, METEOR scores are used to measure the efficacy of the model which show improvement inperformance of the caption generation process.
机译：图像字幕是根据图像的内容为给定图像生成字幕。为了有效地描述图像，需要从图像中提取尽可能多的信息。除了检测物体的存在及其相对方位之外，打算作为图像主题的各个目的是另一个重要信息，可以将其与模型结合使用以提高字幕生成系统的效率。唯一的目的是在模仿人的方法的图像的上下文上施加额外的推力，因为可能与表示图像的上下文无关的对象的存在不应该是所生成字幕的一部分。在这项工作中，重点是检测与图像有关的主题，以指导新颖的基于深度学习的编码器-解码器框架为图像生成字幕。基于从MSCOCO 2017训练数据集获得的结果，该方法与一些较早的最新模型进行了比较。 BLEU，CIDEr，ROGUE-L，METEOR得分用于衡量模型的有效性，该模型显示字幕生成过程的性能有所提高。

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