Improving Intra- and Inter-Modality Visual Relation for Image Captioning.
Yong WangWenkai ZhangQing LiuZhengyuan ZhangXin GaoXian SunPublished in: ACM Multimedia (2020)
Keyphrases
- input image
- low level
- image content
- image analysis
- image data
- multiscale
- visual perception
- image segmentation
- image classification
- high resolution
- image features
- image collections
- edge detection
- visually similar
- template matching
- hough transform
- visual data
- region of interest
- visual cues
- visual information
- image structure
- image pixels
- image matching
- segmentation method
- spatial layout
- multi modal
- image retrieval
- visual appearance
- human observers
- visual attributes
- web image search
- image regions
- single image
- segmentation algorithm
- image representation
- high level
- spatial relations
- test images
- medical images
- visual input
- multiresolution
- medical image retrieval