Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence.

Seungryong Kim Dongbo Min Stephen Lin Kwanghoon Sohn

Published in: CoRR (2016)

Keyphrases

cross modal
multi modal
image retrieval
multimedia retrieval
visual recognition
object recognition
visual similarity
keypoints
multimedia databases
perceptual information
image matching
visual data
relevance feedback
action recognition
text retrieval
low level features