Inserting Faces inside Captions: Image Captioning with Attention Guided Merging.
Yannis TevissenKhalil GuetariMarine TasselErwan KerlerouxFrédéric PetitpontPublished in: CoRR (2024)
Keyphrases
- input image
- image classification
- image data
- image retrieval
- single image
- multiscale
- image features
- image segmentation
- image analysis
- image content
- image representation
- image pixels
- visual features
- template matching
- feature points
- test images
- similarity measure
- segmentation algorithm
- hough transform
- image collections
- detecting faces
- computer vision
- denoising
- image regions
- light source
- low level
- visual attention
- image structure