XFlow: 1D-2D Cross-modal Deep Neural Networks for Audiovisual Classification.

Catalina Cangea Petar Velickovic Pietro Liò

Published in: CoRR (2017)

Keyphrases

cross modal
neural network
pattern recognition
multi modal
machine learning
text classification
supervised learning
feature extraction
feature vectors
image classification
visual recognition
feature space
training set
knn
relevance feedback
multimedia content