An End-to-End Blind Image Quality Assessment Method Using a Recurrent Network and Self-Attention

Mingliang ZHOU, Xuting LAN, Xuekai WEI*, Xingran LIAO, Qin MAO*, Yutong LI, Chao WU, Tao XIANG, Bin FANG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

12 Citations (Scopus)


In this paper, we propose a blind image quality assessment (BIQA) method using self-attention and a recurrent neural network (RNN); this approach can effectively capture both local and global information from an input image. The implementation of our constructed deep no-reference (NR) assessment framework does not rely on any convolutional operations. First, the capture step for obtaining locally significant information is performed by a self-attention operation inside a divided window. Second, we design a serialized feature input memory subnetwork to fuse the global features of the image. Finally, all the integrated features are uniformly mapped to the target score. The experimental results obtained on publicly available benchmark IQA databases show that our approach outperforms other state-of-the-art algorithms.

Original languageEnglish
Pages (from-to)369-377
Number of pages9
JournalIEEE Transactions on Broadcasting
Issue number2
Early online date28 Oct 2022
Publication statusPublished - Jun 2023
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 1963-12012 IEEE.


  • Blind image quality assessment
  • recurrent neural network
  • self-attention


Dive into the research topics of 'An End-to-End Blind Image Quality Assessment Method Using a Recurrent Network and Self-Attention'. Together they form a unique fingerprint.

Cite this