Visual enhanced gLSTM for image captioning.
Jing ZhangKangkang LiZhenkun WangXianwen ZhaoZhe WangPublished in: Expert Syst. Appl. (2021)
Keyphrases
- input image
- image data
- low level
- image features
- image classification
- visual perception
- single image
- template matching
- visual appearance
- human visual
- image regions
- image representation
- image segmentation
- image content
- image matching
- multiscale
- image analysis
- image retrieval
- visual data
- image collections
- visual features
- spatial layout
- spatial information
- visual similarity
- web images
- visual cues
- image pixels
- pixel values
- hough transform
- object detection
- medical image retrieval
- visual concepts
- image structure
- region of interest
- segmentation method
- edge detection
- image database
- high resolution
- high level