.png){kind=icon}
返回
Hybrid attention network for image captioning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2022.102238.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine attention mechanisms are widely used in the task of image captioning. Such mechanisms dynamically focus on different regions to guide the word generation process. However, existing attention models may fail to concentrate on correct regions and mislead the word prediction without explicit supervision. In this study, we exploit the human captioning attention encoding rich information that human beings perceive during captioning, and propose a novel Hybrid Attention Network (HAN) that incorporates the prevailing machine attention mechanisms with human captioning attention. The proposed HAN addresses the problem of object hallucinationby re-weighting bottom-up attention, and improves the diversity of the generated captioning by complementing top-down attention with human captioning attention. Extensive experiments are conducted on Flickr30K and MS COCO datasets, demonstrating that the proposed method effectively improves the performance of the current image captioning methods.
Keyword:
Human attention
Attention mechanism
Image captioning
期刊
IF:
3.4
论文数:
2.3K
被引数:
3.2K
机构
S
引用论文
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention更加关注显著性: 具有显著性和上下文关注的图像字幕
PREAI
分享收藏分享收藏
Boosting convolutional image captioning with semantic content and visual relationship.png)
DISPLAYS
DISPLAYSIF3.4
PREAI
分享收藏
查看更多内容