Beyond Vision: A Multimodal Recurrent Attention Convolutional Neural Network for Unified Image Aesthetic Prediction Tasks.
Xiaodan ZhangXinbo GaoWen LuLihuo HeJie LiPublished in: IEEE Trans. Multim. (2021)
Keyphrases
- convolutional neural network
- single image
- image data
- input image
- image features
- image content
- multiscale
- image analysis
- image segmentation
- template matching
- image retrieval
- visual perception
- region of interest
- low level
- test images
- keypoints
- segmentation method
- image representation
- feature points
- image classification
- computer vision
- low level image processing
- vision system
- image matching
- edge detection
- image synthesis
- image processing
- feature extraction
- image pixels
- pixel values
- recurrent neural networks
- image collections
- visual attention
- multi modal
- multiresolution
- high resolution
- gray level
- real time