The image captures an audience attending a presentation during the CVPR (Conference on Computer Vision and Pattern Recognition) event held in Seattle. The large screen at the front displays a detailed slide titled "Gromov-Wasserstein for Encoding Structural Priors," presented by an academic from Aarhus University. The slide features mathematical formulations and key points related to this topic. The room is filled with attentive participants sitting on chairs, some of whom are taking notes or photos of the presentation. The venue has an industrial-like ceiling with exposed beams and lighting fixtures, contributing to a modern conference atmosphere. The event logo and various informative slides are visible, indicating a focused and educational environment for the attendees.
Text transcribed from the image:
omov-Wasserstein for
coding Structural Priors
atively) general formulation for (discrete) GW problems:
minimize ELC.CT
CVPR
JUNE 17-21, 2024
MIT SEATTLE, W
Gromov-Wasserstein for
Encoding Structural Priors
A (relatively) general t
ete) GW problems
st
Tix N
TINIK
t matrices C" e RN and C
a" function between cost i
Cost matric
"Loss" fur
nts &: RXR-R
Gromov-Wasserstein for
Encoding Structural Priors
A (relatively) general formulation for (discrete) GW problems:
minimize Σike[N] L(CC)TiTkl
TERNXK
s.t.
j,le[K]
T1K = N,
T1N=1K,
> Cost matrices C" E RNXN and Ca Є RKXK
Australian
National
University
>"Loss" function between cost matrix elements L: RX R-R
MegXu and Shephen Gould Semporaly Content Undanced Optimal Transport for Unsupervised