RegionCLIP: Region-based Language-Image Pretraining.

Yiwu Zhong Jianwei Yang Pengchuan Zhang Chunyuan Li Noel Codella Liunian Harold Li Luowei Zhou Xiyang Dai Lu Yuan Yin Li Jianfeng Gao

Published in: CVPR (2022)

Keyphrases

input image
image data
image features
single image
template matching
image retrieval
image content
image segmentation
image analysis
pixel values
image representation
vector field
multiscale
image noise
image collections
language learning
image classification
hough transform
spatial information
segmentation method
region of interest
region matching
image matching
post processing
test images
feature points
image database
high resolution
multiresolution