###
计算机系统应用:2020,29(5):245-251
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于双路细化注意力机制的图像描述模型
(中国石油大学(华东) 计算机科学与技术学院, 青岛 266580)
Image Captioning Based on Dual Refined Attention
(College of Computer Science and Technology, China University of Petroleum, Qingdao 266580, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 83次   下载 64
投稿时间:2019-10-07    修订日期:2019-11-07
中文摘要: 图像描述是连接计算机视觉与自然语言处理两大人工智能领域内的一项重要任务.近几年来,基于注意力机制的编码器-解码器架构在图像描述领域内取得了显著的进展.然而,许多基于注意力机制的图像描述模型仅使用了单一的注意力机制.本文提出了一种基于双路细化注意力机制的图像描述模型,该模型同时使用了空间注意力机制与通道注意力机制,并且使用了细化图像特征的模块,对图像特征进行进一步细化处理,过滤掉图像中的冗余与不相关的特征.我们在MS COCO数据集上进行实验来验证本文模型的有效性,实验结果表明本文的基于双路细化注意力机制的图像描述模型与传统方法相比有显著的优越性.
Abstract:Image captioning is an important task, which connects computer vision and natural language processing, two major artificial intelligence fields. In recent years, encoder-decoder frameworks integrated with attention mechanism have made significant process in captioning. However, many attention-based methods only use spatial attention mechanism. In this study, we propose a novel dual refined attention model for image captioning. In the proposed model, we use not only spatial attention but also channel-wise attention and then use a refine module to refine the image features. By using the refine module, the proposed model can filter the redundant and irrelevant features in the attended image features. We validate the proposed model on MSCOCO dataset via various evaluation metrics, and the results show the effectiveness of the proposed model.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
丛璐文.基于双路细化注意力机制的图像描述模型.计算机系统应用,2020,29(5):245-251
CONG Lu-Wen.Image Captioning Based on Dual Refined Attention.COMPUTER SYSTEMS APPLICATIONS,2020,29(5):245-251

用微信扫一扫

用微信扫一扫