Vision-to-Language Tasks Based on Attributes and Attention Mechanism | |
Li, Xuelong1,2; Yuan, Aihong3,4; Lu, Xiaoqiang3 | |
作者部门 | 光谱成像技术研究室 |
2021-02 | |
发表期刊 | IEEE TRANSACTIONS ON CYBERNETICS |
ISSN | 2168-2267;2168-2275 |
卷号 | 51期号:2页码:913-926 |
产权排序 | 3 |
摘要 | Vision-to-language tasks aim to integrate computer vision and natural language processing together, which has attracted the attention of many researchers. For typical approaches, they encode image into feature representations and decode it into natural language sentences. While they neglect high-level semantic concepts and subtle relationships between image regions and natural language elements. To make full use of these information, this paper attempt to exploit the text-guided attention and semantic-guided attention (SA) to find the more correlated spatial information and reduce the semantic gap between vision and language. Our method includes two-level attention networks. One is the text-guided attention network which is used to select the text-related regions. The other is SA network which is used to highlight the concept-related regions and the region-related concepts. At last, all these information are incorporated to generate captions or answers. Practically, image captioning and visual question answering experiments have been carried out, and the experimental results have shown the excellent performance of the proposed approach. |
关键词 | Deep learning image captioning multimodal visual question answering (VQA) |
DOI | 10.1109/TCYB.2019.2914351 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000608690900036 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/94280 |
专题 | 光谱成像技术研究室 |
通讯作者 | Lu, Xiaoqiang |
作者单位 | 1.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Peoples R China 2.Northwestern Polytech Univ, Ctr Opt Imagery Anal & Learning, Xian 710072, Peoples R China 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol CAS, Xian 710119, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Xuelong,Yuan, Aihong,Lu, Xiaoqiang. Vision-to-Language Tasks Based on Attributes and Attention Mechanism[J]. IEEE TRANSACTIONS ON CYBERNETICS,2021,51(2):913-926. |
APA | Li, Xuelong,Yuan, Aihong,&Lu, Xiaoqiang.(2021).Vision-to-Language Tasks Based on Attributes and Attention Mechanism.IEEE TRANSACTIONS ON CYBERNETICS,51(2),913-926. |
MLA | Li, Xuelong,et al."Vision-to-Language Tasks Based on Attributes and Attention Mechanism".IEEE TRANSACTIONS ON CYBERNETICS 51.2(2021):913-926. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Vision-to-Language T(3082KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论