Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Author:
Affiliation:
1. University of Science and Technology of China, Hefei, China
2. China Merchants Bank, Chengdu, China
Funder
National Key Research and Development Program of China
Supercomputing Center of University of Science and Technology of China
Publisher
ACM
Link
https://dl.acm.org/doi/pdf/10.1145/3581783.3611913
Reference47 articles.
1. Scene Text Image Super-Resolution in the Wild
2. A novel character segmentation-reconstruction approach for license plate recognition
3. An automatic road sign recognition system based on a computational model of human recognition processing
4. Street View Text Recognition With Deep Learning for Urban Scene Understanding in Intelligent Transportation Systems
5. Hoang Danh Liem , Nguyen Duc Minh , Nguyen Bao Trung, Hoang Tien Duc, Pham Hoang Hiep, Doan Viet Dung, and Dang Hoang Vu. Fvi: An end-to-end vietnamese identification card detection and recognition in images. pages 338 -- 340 , 2018 . Hoang Danh Liem, Nguyen Duc Minh, Nguyen Bao Trung, Hoang Tien Duc, Pham Hoang Hiep, Doan Viet Dung, and Dang Hoang Vu. Fvi: An end-to-end vietnamese identification card detection and recognition in images. pages 338--340, 2018.
Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. SECANet: A structure‐enhanced attention network with dual‐domain contrastive learning for scene text image super‐resolution;Electronics Letters;2023-12
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3