%0 Generic
%A Neverova, N
%A Kokkinos, I
%D 2018
%E Shao, L
%E Shum, HPH
%E Hospedales, T
%F discovery:10060971
%I BMVA Press
%T Mass Displacement Networks
%U https://discovery.ucl.ac.uk/id/eprint/10060971/
%V 29
%X 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.
%Z This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.