1 code implementation • spnlp (ACL) 2022 • Guirong Fu, Zhao Meng, Zhen Han, Zifeng Ding, Yunpu Ma, Matthias Schubert, Volker Tresp, Roger Wattenhofer
In this paper, we tackle the temporal knowledge graph completion task by proposing TempCaps, which is a Capsule network-based embedding model for Temporal knowledge graph completion.
no code implementations • 11 Jan 2024 • Niklas Strauß, Matthias Schubert
Furthermore, we propose a novel message-passing module for learning future inter-action correlations in the given environment.
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 • ICCV 2023 • Maximilian Bernhard, Niklas Strauß, Matthias Schubert
Our approach outperforms existing change detection methods by an absolute 11. 7\% and 18. 4\% in terms of binary change IoU on DynamicEarthNet and HRSCD, respectively.
1 code implementation • 24 Oct 2022 • Maximilian Bernhard, Matthias Schubert
In order to create the necessary training annotations for object detectors, imagery can be georeferenced and combined with data from other sources, such as points of interest localized by GPS sensors.
1 code implementation • 12 Oct 2022 • Yatin Chaudhary, Pranav Rai, Matthias Schubert, Hinrich Schütze, Pankaj Gupta
The objective of Federated Continual Learning (FCL) is to improve deep learning models over life time at each client by (relevant and efficient) knowledge transfer without sharing 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 • 22 Jul 2022 • Christian M. M. Frey, Matthias Schubert
Semantic Web or Knowledge Graphs (KG) emerged to one of the most important information source for intelligent systems requiring access to structured knowledge.
1 code implementation • 14 Feb 2022 • Tanveer Hannan, Rajat Koner, Jonathan Kobold, Matthias Schubert
Video Object Segmentation (VOS) has been targeted by various fully-supervised and self-supervised approaches.
no code implementations • 22 Nov 2021 • Jason Jooste, Michael Fromm, Matthias Schubert
Increasing the resolution of this height information also showed little effect.
no code implementations • 27 Oct 2021 • Christian M. M. Frey, Yunpu Ma, Matthias Schubert
In temporal Knowledge Graphs (tKGs), the temporal dimension is attached to facts in a knowledge base resulting in quadruples between entities such as (Nintendo, released, Super Mario, Sep-13-1985), where the predicate holds within a time interval or at a timestamp.
no code implementations • 20 Oct 2021 • Christian M. M. Frey, Yunpu Ma, Matthias Schubert
Intuitively, by increasing the number of experts, the models gain in expressiveness such that a node's representation is solely based on nodes that are located within the receptive field of an expert.
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.
4 code implementations • 20 Mar 2020 • Jakaria Rabbi, Nilanjan Ray, Matthias Schubert, Subir Chowdhury, Dennis Chao
Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance.
1 code implementation • 29 Jan 2020 • Diana Davletshina, Valentyn Melnychuk, Viet Tran, Hitansh Singla, Max Berrendorf, Evgeniy Faerman, Michael Fromm, Matthias Schubert
Therefore, we adopt state-of-the-art approaches for unsupervised learning to detect anomalies and show how the outputs of these methods can be explained.
no code implementations • 15 Nov 2019 • Teodora Pandeva, Matthias Schubert
Moreover, MMGAN allows for clustering real data according to the learned data manifold in the latent space.
no code implementations • 15 Feb 2018 • Evgeniy Faerman, Felix Borutta, Julian Busch, Matthias Schubert
Precisely, we propose a new node embedding which is based on the class labels in the local neighborhood of a node.
no code implementations • ICLR 2018 • Jindong Gu, Matthias Schubert, Volker Tresp
In the adversarial process of training CorGAN, the Generator is supposed to generate outlier samples for negative class, and the Discriminator as an one-class classifier is trained to distinguish data from training datasets (i. e. positive class) and generated data from the Generator (i. e. negative class).
no code implementations • 24 Mar 2016 • Anders Drachen, Matthew Yancey, John Maguire, Derrek Chu, Iris Yuhui Wang, Tobias Mahlmann, Matthias Schubert, Diego Klabjan
Results indicate that spatio-temporal behavior of MOBA teams is related to team skill, with professional teams having smaller within-team distances and conducting more zone changes than amateur teams.