Unsupervised Cross-Modal Deep-Model Adaptation for Audio-Visual Re-identification with Wearable Cameras.

Alessio Brutti Andrea Cavallaro

Published in: ICCV Workshops (2017)

Keyphrases

audio visual
cross modal
multi modal
visual data
visual information
human computer interaction
high dimensional
multimedia
spatio temporal
image annotation
visual similarity
image data
feature vectors
visual features
computer vision
visual content
visual recognition
multimedia retrieval
feature selection