EMU: Effective Multi-Hot Encoding Net for Lightweight Scene Text Recognition With a Large Character Set
Author:
Affiliation:
1. Visual Computing Group, Ping An Property & Casualty Insurance Company, Shenzhen, China
2. School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
Funder
National Natural Science Foundation of China
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Media Technology
Link
http://xplorestaging.ieee.org/ielx7/76/9849156/09691322.pdf?arnumber=9691322
Reference67 articles.
1. Learning both weights and connections for efficient neural network;han;Proc Adv Neural Inf Process Systems,2015
2. Deep Compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding;han;Proc Int Conf Learn Represent,2016
3. Q8BERT: Quantized 8Bit BERT
4. Low-bit Quantization of Neural Networks for Efficient Inference
5. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Cited by 12 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. NDOrder: Exploring a novel decoding order for scene text recognition;Expert Systems with Applications;2024-09
2. RRTrN: A lightweight and effective backbone for scene text recognition;Expert Systems with Applications;2024-06
3. Ensemble Deep Learning Technique based English Text Detection and Recognition Approach;2024 Second International Conference on Data Science and Information System (ICDSIS);2024-05-17
4. HAFE: A Hierarchical Awareness and Feature Enhancement Network for Scene Text Recognition;Knowledge-Based Systems;2024-01
5. CLCRNet: An Optical Character Recognition Network for Cigarette Laser Code;IEEE Transactions on Instrumentation and Measurement;2024
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