C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative Gap.
William TheisenWalter J. ScheirerPublished in: CoRR (2023)
Keyphrases
- input image
- image data
- image content
- single image
- image features
- image classification
- image segmentation
- image representation
- image analysis
- image retrieval
- low level
- image matching
- edge detection
- pixel values
- image collections
- multiscale
- image pixels
- region of interest
- spatial information
- hough transform
- image sequences
- feature points
- high resolution
- computer vision
- image search
- text information
- web images
- textual and visual information
- bounding box
- template matching
- test images
- semantic information
- video data
- segmentation algorithm
- object recognition
- keywords
- face recognition
- high level