Effective Multimodal Encoding for Image Paragraph Captioning.
Thanh-Son NguyenBasura FernandoPublished in: IEEE Trans. Image Process. (2022)
Keyphrases
- image data
- input image
- image features
- image classification
- single image
- image representation
- image analysis
- image segmentation
- image collections
- image retrieval
- template matching
- vector field
- multiscale
- edge detection
- image matching
- image content
- multi modal
- image pixels
- test images
- high resolution
- image structure
- segmentation method
- feature points
- image regions
- similarity measure
- binary images
- image quality
- low level
- high quality
- face recognition