IQA/VQA

https://github.com/weizhou-geek/Recent-Image-Quality-Related-Papers

 

https://github.com/ysyscool/SGDNet

 

搞懂 Vision Transformer 原理和代码，看这篇技术综述就够了（十一）

https://bbs.cvmart.net/articles/4795

 

#每日五分钟一读# Image Quality Assessment 

https://zhuanlan.zhihu.com/p/370818013

 

 TRIQ：用于图像质量评估的Transformer

https://zhuanlan.zhihu.com/p/342093995

 

https://www.zhihu.com/question/498364155/answer/2220403764

 

OCR文字识别-基于CTC/Attention/ACE的三大解码算法

https://jishuin.proginn.com/p/763bfbd6695c

 

完全解析RNN, Seq2Seq, Attention注意力机制 

https://zhuanlan.zhihu.com/p/51383402

 

OCR文字识别—基于CTC/Attention/ACE的三大解码算法

https://zhuanlan.zhihu.com/p/398053504

 

 

 

人工智能 文献总结《Learning Spatiotemporal Features with 3D Convolutional Networks》(附TensorFlow代码)

https://www.dazhuanlan.com/pengrubinndip/topics/1203426

 

【论文阅读】Learning Spatiotemporal Features with 3D Convolutional Networks

https://blog.csdn.net/zzmshuai/article/details/84866514

 

图像质量评估（IQA）——“KonCept512” 论文解读

https://blog.csdn.net/huangfei711/article/details/109146292

 

 

https://zhuanlan.zhihu.com/p/35388036

https://github.com/Ontheway361/C3D