A task where AI writes a plain sentence about an image.
Image captioning is your camera roll with a tiny sports announcer. It says, “Dog on sofa. Pizza in danger.”
It turns pictures into words. You meet it in photo search, screen readers, and online shops.
Computer Vision
Image captioning says what the AI sees in plain words.
Multimodal AI
It connects image understanding with text writing.
COCO Dataset
COCO provides many images with human-written captions.
BLEU
BLEU roughly checks how close a caption is to reference captions.