PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3.

Yushi Hu Hang Hua Zhengyuan Yang Weijia Shi Noah A. Smith Jiebo Luo

Published in: ICCV (2023)

Keyphrases

input image
image content
image data
image pixels
multiscale
image classification
image analysis
image features
image segmentation
image regions
edge detection
image retrieval
single image
image collections
low level
high resolution
image database
image representation
similarity measure
image matching
object recognition
feature points
image sequences
computer vision
image quality assessment