CMA: Cross-modal attention for 6D object pose estimation.

Lu Zou Zhangjin Huang Fangjun Wang Zhouwang Yang Guoping Wang

Published in: Comput. Graph. (2021)

Keyphrases

pose estimation
d objects
cross modal
multi modal
human body
object recognition
viewpoint
degrees of freedom
three dimensional
shape descriptors
depth images
multi view
object classes
range data
pose parameters
multiple views
human pose
invariant recognition
image retrieval
visual data
image annotation