.png){kind=icon}
返回
Dual-CNN: A Convolutional language decoder for paragraph image captioning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2020.02.041.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The task of paragraph image captioning aims to generate a coherent paragraph describing a given image. However, due to their limited ability to capture long-term dependency, recurrent neural network or long-short term memory based decoders could hardly generate satisfactory textual descriptions with a long paragraph. In addition, the training inefficiency in the sequential decoders is significantly observed. Motivated by the advantage of convolutional neural network (i.e., CNN), in this paper, we propose a Dual-CNN decoder with long-term memory ability and parallel computation, which can produce a semantically coherent paragraph for an image. Our Dual-CNN model is evaluated on the Stanford image-paragraph dataset. Extensive experiments demonstrate that our Dual-CNN achieves comparable results compared with state-of-the-art models. Furthermore, the diversity and coherence of generated paragraphs are analyzed to show the superiority of our approach. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Deep learning
Language and vision
Convolutional neural networks
Image captioning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉
OAAI
OAAI分享收藏VD-SAN: Visual-Densely Semantic Attention Network for Image Caption Generation.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏 没有更多内容
没有更多内容