Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone.
Zi-Yi DouAishwarya KamathZhe GanPengchuan ZhangJianfeng WangLinjie LiZicheng LiuCe LiuYann LeCunNanyun PengJianfeng GaoLijuan WangPublished in: CoRR (2022)
Keyphrases
- coarse to fine
- multiscale
- multiresolution
- hierarchical segmentation
- object detection
- image registration
- hierarchical representation
- matching scheme
- image fusion
- computer vision
- active shape model
- training set
- optical flow estimation
- machine learning
- dynamic programming
- deformable contour
- image pyramid
- image processing
- pattern recognition
- wavelet transform
- level set
- image data
- feature correspondences