2017-2018论文更新

本文汇总了2017年至2018年间在计算机视觉领域的文本识别与检测方面的最新研究成果。涉及场景文本识别、任意方向文本检测及端到端解决方案等多个方面,覆盖了从ICCV、CVPR到IJCAI等顶级会议的论文。
部署运行你感兴趣的模型镜像

2017-2018论文更新

识别

  1. XiangBai——【PAMI2018】ASTER_An Attentional Scene Text Recognizer with Flexible Rectification

  2. Zhanzhan Cheng——【CVPR2018】AON_Towards Arbitrarily-Oriented Text Recognition

  3. Zhanzhan Cheng——【CVPR2018】Edit Probability for Scene Text Recognition

  4. Christian Bartz——【AAAI2018】SEE_Towards Semi-Supervised End-to-End Scene Text Recognition

  5. Zhanzhan Cheng——【ICCV2017】Focusing Attention_Towards Accurate Text Recognition in Natural Images

检测

  1. Lianwen Jin——【2017】Detecting Curve Text in the Wild_New Dataset and New Solution

  2. Zichuan Liu——【CVPR2018】Learning Markov Clustering Networks for Scene Text Detection

  3. Tong He——【CVPR2018】Single Shot TextSpotter with Explicit Alignment and Attention

  4. XiangBai——【CVPR2018】Rotation-Sensitive Regression for Oriented Scene Text Detection

  5. Tong He——【ICCV2017】Single Shot Text Detector with Regional Attention

  6. Alibaba——【IJCAI2018】IncepText_A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

  7. Lianwen Jin——【AAAI2018】Feature Enhancement Network_A Refined Scene Text Detector

  8. Andrei Polzounov——【ICIP2017】WordFence_Text Detection in Natural Images with Border Awareness

  9. Suman Ghosh——【ICDAR2017】R-PHOC_Segmentation-Free Word Spotting using CNN

  10. Xiangyu Zhu——【IAPR2018】Deep Residual Text Detection Network for Scene Text

  11. Daitao Xing——【2017】ArbiText_Arbitrary-Oriented Text Detection in Unconstrained Scene

  12. Xiaoyu Yu——【2018】Boosting up Scene Text Detectors with Guided CNN

  13. Li Xiang——【2018】Shape Robust Text Detection with Progressive Scale Expansion Network

端到端

  1. XiangBai——【CVPR2018】Mask TextSpotter_An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
  2. TongHe——【CVPR2018】An end-to-end TextSpotter with Explicit Alignment and Attention
  3. Xuebo Liu——【CVPR2108】FOTS_Fast Oriented Text Spotting with a Unified Network

转载于:https://www.cnblogs.com/lillylin/p/9314957.html

您可能感兴趣的与本文相关的镜像

Wan2.2-T2V-A5B

Wan2.2-T2V-A5B

文生视频
Wan2.2

Wan2.2是由通义万相开源高效文本到视频生成模型,是有​50亿参数的轻量级视频生成模型,专为快速内容创作优化。支持480P视频生成,具备优秀的时序连贯性和运动推理能力

评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符  | 博主筛选后可见
 
红包 添加红包
表情包 插入表情
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值