首页> 外文会议>Workshop on intelligent interactive systems and language generation >Generating Descriptions for Sequential Images with Local-Object Attention and Global Semantic Context Modelling
【24h】

Generating Descriptions for Sequential Images with Local-Object Attention and Global Semantic Context Modelling

机译:使用局部对象注意和全局语义上下文建模生成顺序图像的描述

获取原文
获取原文并翻译 | 示例

摘要

In this paper, we propose an end-to-end CNN-LSTM model for generating descriptions for sequential images with a local-object attention mechanism. To generate coherent descriptions, we capture global semantic context using a multilayer perceptron, which learns the dependencies between sequential images. A paralleled LSTM network is exploited for decoding the sequence descriptions. Experimental results show that our model outperforms the baseline across three different evaluation metrics on the datasets published by Microsoft.
机译:在本文中,我们提出了一种端到端CNN-LSTM模型,用于使用局部对象注意机制生成顺序图像的描述。为了生成连贯的描述,我们使用多层感知器捕获全局语义上下文,该感知器学习顺序图像之间的依赖性。利用并行LSTM网络对序列描述进行解码。实验结果表明,在Microsoft发布的数据集上,我们的模型在三个不同的评估指标上均优于基线。

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