1 code implementation • 16 Apr 2024 • Marah Halawa, Florian Blume, Pia Bideau, Martin Maier, Rasha Abdel Rahman, Olaf Hellwich
To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task.
Ranked #1 on Emotion Recognition in Conversation on MELD (Weighted Accuracy metric)
Emotion Classification Emotion Recognition in Conversation +2
no code implementations • 28 Nov 2023 • Boris Meinardus, Mariusz Trzeciakiewicz, Tim Herzig, Monika Kwiatkowski, Simon Matern, Olaf Hellwich
We present Decomposer, a semi-supervised reconstruction model that decomposes distorted image sequences into their fundamental building blocks - the original image and the applied augmentations, i. e., shadow, light, and occlusions.
no code implementations • 17 Oct 2023 • Monika Kwiatkowski, Simon Matern, Olaf Hellwich
When taking images of some occluded content, one is often faced with the problem that every individual image frame contains unwanted artifacts, but a collection of images contains all relevant information if properly aligned and aggregated.
1 code implementation • 19 May 2023 • Monika Kwiatkowski, Simon Matern, Olaf Hellwich
Our data generation pipeline is customizable and can be applied to any existing dataset, serving as a data augmentation to further improve the feature learning of any existing method.
1 code implementation • 3 Aug 2022 • Dominik Kuhnke, Monika Kwiatkowski, Olaf Hellwich
Our experiments demonstrate that both approaches are suitable for solving and automating honeycomb detection.
1 code implementation • 3 Aug 2022 • Tianyi Hu, Monika Kwiatkowski, Simon Matern, Olaf Hellwich
A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search.
no code implementations • 18 Jul 2022 • Marah Halawa, Olaf Hellwich, Pia Bideau
To that end, we propose a novel action-based contrastive learning loss, that utilizes pedestrian action information to improve the learned trajectory embeddings.
no code implementations • 10 Jun 2021 • Nicolas Roth, Pia Bideau, Olaf Hellwich, Martin Rolfs, Klaus Obermayer
We model this active scene exploration as a sequential decision making process.
no code implementations • 16 Aug 2020 • Marah Halawa, Manuel Wöllhaf, Eduardo Vellasques, Urko Sánchez Sanz, Olaf Hellwich
One common strategy to tackle such a problem is to learn disentangled representations for the different factors of variation of the observed data using adversarial learning.
no code implementations • 1 Nov 2013 • Olivier D'Hondt, Stéphane Guillaso, Olaf Hellwich
In this paper, we introduce an iterative speckle filtering method for polarimetric SAR (PolSAR) images based on the bilateral filter.