Dear all,
you are cordially invited to join the master's defense of Rene Kollmann on 20.1.21 at 10 am. You can join via Zoom as follows:
Meeting link: https://uni-bamberg.zoom.us/j/96252437758
Meeting-ID: 962 5243 7758
Password: $c$r7i
Rene Kollmann will defend his thesis about Explaining Facial Expressions
with Temporal Prototypes.
Abstract:
Accurately determining the emotional state of a person is a difficult task for
both - humans as well as machines. Automatic detection and evaluation of facial
expressions is particularly important if people are unable to communicate
by themselves. Identifying the presence of action units in a human's face is
the foundation of quantifying which emotion is expressed. To automate the
detection process of action units neural networks have been trained. However,
the black-box nature of deep neural networks provides no insight on the relevant
features identied during the decision process. Additional approaches of
explainable articial intelligence have to be applied to provide and explanation
why the network came to a certain conclusion. In this work "Layer-Wise Relevance
Propagation" (LRP) in combination with the meta analysis approach
"Spectral Relevance Analysis" (SpRAy) is used to derive temporal prototypes
in video sequences. Temporal prototypes provide an aggregated view on the
prediction of the network by grouping together similar predictions. Additionally,
a specic visualization method for temporal prototypes is presented that
highlights the most relevant areas for a prediction of an action unit.
Based on the above, this work shall provide the foundation for a new application
domain specic explanation approach that is supposed to help researchers and
experts to gain a deeper understanding of how the underlying network performs
its decision on which action units are active and which are not.