Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training.

Arian Bakhtiarnia Qi Zhang Alexandros Iosifidis

Published in: CoRR (2022)

Keyphrases

compressed images
image compression
artifact reduction
visual quality
reconstructed image
compressed domain
image quality
bitstream
compression ratio
dct domain
training set
discrete cosine transform
face recognition
wavelet transform