Leveraging mid-level deep representations for predicting face attributes in the wild.

Yang Zhong Josephine Sullivan Haibo Li

Published in: ICIP (2016)

Keyphrases

mid level
low level
high level
low level features
visual information
visual cues
action recognition
superpixels
levels of abstraction
event detection
face images
perceptual grouping
visual concepts
higher level
multiscale
visual features
semantic gap
semantic information
machine learning