TY  - GEN
Y1  - 2018/09//
AV  - public
TI  - Mass Displacement Networks
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
UR  - http://bmvc2018.org/programmedetail.html
PB  - BMVA Press
ID  - discovery10060971
N2  - Despite the large improvements in performance attained by deep learning in computer
vision, one can often further improve results with some additional post-processing
that exploits the geometric nature of the underlying task. This commonly involves displacing
the posterior distribution of a CNN in a way that makes it more appropriate for
the task at hand, e.g. better aligned with local image features, or more compact. In this
work we integrate this geometric post-processing within a deep architecture, introducing
a differentiable and probabilistically sound counterpart to the common geometric voting
technique used for evidence accumulation in vision. We refer to the resulting neural models
as Mass Displacement Networks (MDNs), and apply them to human pose estimation
in two distinct setups: (a) landmark localization, where we collapse a distribution to a
point, allowing for precise localization of body keypoints and (b) communication across
body parts, where we transfer evidence from one part to the other, allowing for a globally
consistent pose estimate. We evaluate on large-scale pose estimation benchmarks, such
as MPII Human Pose and COCO datasets, and report systematic improvements.
A1  - Neverova, N
A1  - Kokkinos, I
T3  - British Machine Vision Conference
ER  -