MAENet: A novel multi-head association attention enhancement network for completing intra-modal interaction in image captioning.
Nannan HuChunxiao FanYue MingFan FengPublished in: Neurocomputing (2023)
Keyphrases
- input image
- image data
- image classification
- image content
- single image
- image features
- multiscale
- image retrieval
- template matching
- contrast enhancement
- human head
- image analysis
- similarity measure
- modal logic
- image collections
- spatial information
- hough transform
- image regions
- keypoints
- human computer interaction
- image representation
- peer to peer
- visual field
- high resolution
- image contrast
- region of interest
- segmentation method
- segmentation algorithm
- edge detection
- multiresolution