Improved weak labels using contextual cues for person identification in videos.

Makarand Tapaswi Martin Bäuml Rainer Stiefelhagen

Published in: FG (2015)

Keyphrases

person identification
contextual cues
tv series
gender classification
video sequences
face recognition
video content
training data
speaker recognition
gait recognition
contextual information
video frames
video data
low resolution
iris images
multi class
high resolution
visual context
pairwise
object recognition