Towards Local Visual Modeling for Image Captioning.
Yiwei MaJiayi JiXiaoshuai SunYiyi ZhouRongrong JiPublished in: CoRR (2023)
Keyphrases
- visual appearance
- input image
- image features
- image data
- image classification
- image segmentation
- image representation
- image analysis
- multiscale
- low level
- visual perception
- visual features
- human visual
- image pixels
- segmentation method
- image regions
- image content
- visually similar
- web images
- template matching
- test images
- image matching
- single image
- visual attributes
- segmentation algorithm
- visual data
- visual cues
- feature points
- edge detection
- computer vision
- region of interest
- pixel values
- image retrieval
- web image search
- image descriptors
- spatial information
- hough transform
- keypoints