Towards Accurate Text-based Image Captioning with Content Diversity Exploration.
Guanghui XuShuaicheng NiuMingkui TanYucheng LuoQing DuQi WuPublished in: CoRR (2021)
Keyphrases
- input image
- image features
- image data
- single image
- image segmentation
- template matching
- image content
- multiscale
- image representation
- image classification
- image analysis
- image pixels
- lighting conditions
- spatial information
- low level
- feature points
- image retrieval
- segmentation method
- region of interest
- completely automated
- textual descriptions
- image set
- test images
- similarity measure
- multimedia
- edge detection
- image matching
- feature extraction
- semantic information
- image collections
- pixel values
- feature vectors
- markov random field