FlexCap: Generating Rich, Localized, and Flexible Captions in Images.
Debidatta DwibediVidhi JainJonathan TompsonAndrew ZissermanYusuf AytarPublished in: CoRR (2024)
Keyphrases
- image database
- image analysis
- three dimensional
- object recognition
- image retrieval
- image data
- image collections
- edge detection
- visual features
- image pixels
- image matching
- segmentation method
- image classification
- input image
- image features
- test images
- rigid body
- image registration
- segmentation algorithm
- ground truth
- image processing
- keypoints
- image regions
- wavelet transform
- lighting conditions
- image set
- image annotation
- multiscale
- image search
- illumination conditions
- similarity measure
- web images