3 citations · 3 across the 4 of their papers we have counts for
5 papers
Causal Inference in Non-linear Time-series using Deep Networks and Knockoff Counterfactuals
Wasim Ahmad, Maha Shadaydeh, Joachim Denzler
Estimating causal relations is vital in understanding the complex interactions in multivariate time series. Non-linear coupling of variables is one of the major challenges inaccura…
Anomaly Attribution of Multivariate Time Series using Counterfactual Reasoning
Violeta Teodora Trifunov, Maha Shadaydeh, Björn Barz +1
There are numerous methods for detecting anomalies in time series, but that is only the first step to understanding them. We strive to exceed this by explaining those anomalies. Th…
Counterfactual Generation with Knockoffs
Oana-Iuliana Popescu, Maha Shadaydeh, Joachim Denzler
Human interpretability of deep neural networks' decisions is crucial, especially in domains where these directly affect human lives. Counterfactual explanations of already trained…
Analysing the Direction of Emotional Influence in Nonverbal Dyadic Communication: A Facial-Expression Study
Maha Shadaydeh, Lea Mueller, Dana Schneider +3
Identifying the direction of emotional influence in a dyadic dialogue is of increasing interest in the psychological sciences with applications in psychotherapy, analysis of politi…
Causal Inference in Nonverbal Dyadic Communication with Relevant Interval Selection and Granger Causality
Lea Müller, Maha Shadaydeh, Martin Thümmel +3
Human nonverbal emotional communication in dyadic dialogs is a process of mutual influence and adaptation. Identifying the direction of influence, or cause-effect relation between…