Cascaded transformer-based networks for wikipedia large-scale image-caption matching.
Nicola MessinaDavide Alessandro CoccominiAndrea EsuliFabrizio FalchiPublished in: Multim. Tools Appl. (2024)
Keyphrases
- template matching
- image data
- image matching
- single image
- feature points
- image features
- input image
- image analysis
- image set
- matching process
- matching scheme
- keypoints
- image retrieval
- image classification
- multiscale
- image pixels
- image representation
- scene matching
- affine invariant
- matching algorithm
- image collections
- feature matching
- region of interest
- social networks
- image content
- image segmentation
- knowledge base
- false matches
- object matching
- similarity measure
- bounding box
- low level
- edge detection
- object recognition
- wordnet
- sift descriptors
- geometric transformations
- graph matching
- affine transformation
- million images
- semantic information
- normalized correlation
- image regions