most citedActive and Incremental Learning with Weak Supervision

21 citations · 23 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2021

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…

cs.LG2021

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…

cs.LG20212 cited

EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task

Christian Requena-Mesa, Vitus Benson, Markus Reichstein +2

Satellite images are snapshots of the Earth surface. We propose to forecast them. We frame Earth surface forecasting as the task of predicting satellite imagery conditioned on futu…

cs.CV2020

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…

cs.LG2020

EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts

Christian Requena-Mesa, Vitus Benson, Joachim Denzler +2

Climate change is global, yet its concrete impacts can strongly vary between different locations in the same region. Seasonal weather forecasts currently operate at the mesoscale (…

cs.CV202021 cited

Active and Incremental Learning with Weak Supervision

Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benc…