Improving multimodal datasets with image captioning.
Thao NguyenSamir Yitzhak GadreGabriel IlharcoSewoong OhLudwig SchmidtPublished in: NeurIPS (2023)
Keyphrases
- image features
- input image
- image data
- single image
- multiscale
- image analysis
- template matching
- image content
- data sets
- image retrieval
- edge detection
- image classification
- test images
- image segmentation
- image noise
- image regions
- multi modal
- high resolution
- image collections
- similarity measure
- image dataset
- segmentation method
- hough transform
- image matching
- region of interest
- million images
- post processing
- benchmark datasets
- image reconstruction
- feature points
- grey level