MMMNet: An End-to-End Multi-Task Deep Convolution Neural Network With Multi-Scale and Multi-Hierarchy Fusion for Blind Image Quality Assessment.
Fan LiYangfan ZhangPamela C. CosmanPublished in: IEEE Trans. Circuits Syst. Video Technol. (2021)
Keyphrases
- end to end
- multi task
- blind image quality assessment
- neural network
- multiscale
- multi task learning
- learning tasks
- multi class
- natural scene statistics
- image processing
- natural images
- learning problems
- image quality
- feature selection
- image quality assessment
- transfer learning
- information gain
- machine learning algorithms
- information theoretic
- image representation
- higher order
- knn
- learning algorithm
- data mining