CLIP-Font: Sementic Self-Supervised Few-Shot Font Generation with Clip.

Jialu Xiong Yefei Wang Jinshan Zeng

Published in: ICASSP (2024)

Keyphrases

character recognition
video clips
document image understanding
key frames
font recognition
low level features
video content
video shots
video data
neural network
video sequences
video database
optical character recognition
computer vision
visual features
information systems
generation process
data mining