no code implementations • 16 Apr 2024 • David Winkel, Niklas Strauß, Matthias Schubert, Thomas Seidl
In this paper, we propose a novel approach to handle allocation constraints based on a decomposition of the constraint action space into a set of unconstrained allocation problems.
1 code implementation • 11 Dec 2023 • Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, Gedas Bertasius
Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance.
no code implementations • 16 Aug 2023 • Sandra Gilhuber, Rasmus Hvingelby, Mang Ling Ada Fok, Thomas Seidl
We conduct experiments with SSL and AL on simulated data challenges and find that random sampling does not mitigate confirmation bias and, in some cases, leads to worse performance than supervised learning.
1 code implementation • 31 Jul 2023 • Sandra Gilhuber, Julian Busch, Daniel Rotthues, Christian M. M. Frey, Thomas Seidl
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data.
1 code implementation • 26 May 2023 • Tanveer Hannan, Rajat Koner, Maximilian Bernhard, Suprosanna Shit, Bjoern Menze, Volker Tresp, Matthias Schubert, Thomas Seidl
Secondly, we propose a novel inter-instance interaction using gate activation as a mask for self-attention.
Ranked #4 on Video Instance Segmentation on YouTube-VIS 2021 (using extra training data)
1 code implementation • 22 Aug 2022 • Rajat Koner, Tanveer Hannan, Suprosanna Shit, Sahand Sharifzadeh, Matthias Schubert, Thomas Seidl, Volker Tresp
We propose three novel components to model short-term and long-term dependency and temporal coherence.
Ranked #5 on Video Instance Segmentation on Youtube-VIS 2022 Validation (using extra training data)
no code implementations • 19 May 2022 • Michael Fromm, Max Berrendorf, Johanna Reiml, Isabelle Mayerhofer, Siddharth Bhargava, Evgeniy Faerman, Thomas Seidl
While there are works on the automated estimation of argument strength, their scope is narrow: they focus on isolated datasets and neglect the interactions with related argument mining tasks, such as argument identification, evidence detection, or emotional appeal.
1 code implementation • EMNLP (insights) 2021 • Nataliia Kees, Michael Fromm, Evgeniy Faerman, Thomas Seidl
High-quality arguments are an essential part of decision-making.
no code implementations • 10 Aug 2021 • Yao Zhang, Yunpu Ma, Thomas Seidl, Volker Tresp
Transformers have improved the state-of-the-art across numerous tasks in sequence modeling.
no code implementations • 5 Mar 2021 • Julian Busch, Anton Kocheturov, Volker Tresp, Thomas Seidl
Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially.
2 code implementations • 10 Dec 2020 • Michael Fromm, Evgeniy Faerman, Max Berrendorf, Siddharth Bhargava, Ruoxia Qi, Yao Zhang, Lukas Dennert, Sophia Selle, Yang Mao, Thomas Seidl
Peer reviewing is a central process in modern research and essential for ensuring high quality and reliability of published work.
1 code implementation • 4 Nov 2020 • Michael Fromm, Max Berrendorf, Sandra Obermeier, Thomas Seidl, Evgeniy Faerman
In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects.
1 code implementation • 23 Oct 2020 • Valentyn Melnychuk, Evgeniy Faerman, Ilja Manakov, Thomas Seidl
Furthermore, our experiments show that exponential moving average (EMA) of model parameters, which is a component of both algorithms, is not needed for our classification problem, as disabling it leaves the outcome unchanged.
Ranked #3 on Retinal OCT Disease Classification on OCT2017
Retinal OCT Disease Classification Semi-Supervised Image Classification +1
1 code implementation • 27 Sep 2020 • Julian Busch, Evgeniy Faerman, Matthias Schubert, Thomas Seidl
Consequently, our model benefits from a constant number of parameters and a constant-size memory footprint, allowing it to scale to considerably larger datasets.
1 code implementation • 4 Mar 2020 • Julian Busch, Jiaxing Pi, Thomas Seidl
We find that our models outperform competitors on all datasets in terms of accuracy with statistical significance.
1 code implementation • 19 Nov 2019 • Max Berrendorf, Evgeniy Faerman, Valentyn Melnychuk, Volker Tresp, Thomas Seidl
In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report on our experiences when applying a Graph Convolutional Network (GCN) based model for this task.
Ranked #33 on Entity Alignment on DBP15k zh-en
no code implementations • 26 May 2019 • Michael Fromm, Evgeniy Faerman, Thomas Seidl
In previous works, the usual approach is to use a standard search engine to extract text parts which are relevant to the given topic and subsequently use an argument recognition algorithm to select arguments from them.