SphereVLAD++: Attention-based and Signal-enhanced Viewpoint Invariant Descriptor.

Shiqi Zhao Peng Yin Ge Yi Sebastian A. Scherer

Published in: CoRR (2022)

Keyphrases

viewpoint invariant
feature detectors
object class
object recognition
cluttered scenes
object representation
wide baseline
image retrieval
action recognition
smooth surfaces
computer vision
visual attention
shape descriptors
feature detection