NWPU-Captions Dataset and MLCA-Net for Remote Sensing Image Captioning

隐藏字幕 计算机科学 背景(考古学) 遥感 水准点(测量) 稳健性(进化) 多样性(控制论) 编码器 人工智能 图像(数学) 地理 地图学 操作系统 基因 考古 化学 生物化学
作者
Qimin Cheng,Haiyan Huang,Yuan Xu,Yuzhuo Zhou,LI Huan-ying,Zhongyuan Wang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:60: 1-19 被引量:37
标识
DOI:10.1109/tgrs.2022.3201474
摘要

Recently, the burgeoning demands for captioning-related applications have inspired great endeavors in the remote sensing community. However, current benchmark datasets are deficient in data volume, category variety, and description richness, which hinders the advancement of new remote sensing image captioning approaches, especially those based on deep learning. To overcome this limitation, we present a larger and more challenging benchmark dataset, termed NWPU-Captions. NWPU-Captions contains 157,500 sentences, with all 31,500 images annotated manually by 7 experienced volunteers. The superiority of NWPU-Captions over current publicly available benchmark datasets not only lies in its much larger scale but also in its wider coverage of complex scenes and the richness and variety of describing vocabularies. Further, a novel encoder-decoder architecture, multi-level and contextual attention network (MLCA-Net), is proposed. MLCA-Net employs a multi-level attention module to adaptively aggregate image features of specific spatial regions and scales and introduces a contextual attention module to explore the latent context hidden in remote sensing images. MLCA-Net improves the flexibility and diversity of the generated captions while keeping their accuracy and conciseness by exploring the properties of scale variations and semantic ambiguity. Finally, the effectiveness, robustness, and generalization of MLCA-Net are proved through extensive experiments on existing datasets and NWPU-Captions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
whl完成签到 ,获得积分10
刚刚
余俊兰发布了新的文献求助10
刚刚
1秒前
少夫人完成签到,获得积分10
2秒前
zwj003完成签到,获得积分0
3秒前
英俊的铭应助Yun采纳,获得10
4秒前
4秒前
lalaland完成签到,获得积分10
4秒前
5秒前
5秒前
鹿立轩完成签到,获得积分10
7秒前
8秒前
Shawn完成签到,获得积分10
8秒前
小蘑菇应助哈哈哈采纳,获得10
8秒前
9秒前
10秒前
李爱国应助恋雅颖月采纳,获得10
10秒前
11秒前
留白发布了新的文献求助10
11秒前
fdkufghkd完成签到,获得积分10
14秒前
15秒前
15秒前
懵懂的幻桃完成签到 ,获得积分10
15秒前
flyfish完成签到,获得积分10
16秒前
16秒前
上官若男应助斯文莺采纳,获得30
17秒前
18秒前
18秒前
19秒前
Yun发布了新的文献求助10
19秒前
19秒前
19秒前
kyra发布了新的文献求助10
20秒前
xiaoze发布了新的文献求助10
20秒前
21秒前
21秒前
小蘑菇应助Yana1311采纳,获得10
22秒前
22秒前
傻傻的小刺猬完成签到,获得积分10
22秒前
22秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988786
求助须知:如何正确求助?哪些是违规求助? 3531116
关于积分的说明 11252493
捐赠科研通 3269766
什么是DOI,文献DOI怎么找? 1804771
邀请新用户注册赠送积分活动 881870
科研通“疑难数据库(出版商)”最低求助积分说明 809021