no code implementations • 23 Apr 2022 • Muhammad Umer Anwaar, Zhihui Pan, Martin Kleinsteuber
The task in Compositional Zero-Shot learning (CZSL) is to learn composition of primitive concepts, i. e. objects and states, in such a way that even their novel compositions can be zero-shot classified.
no code implementations • 29 Oct 2021 • Rayyan Ahmad Khan, Martin Kleinsteuber
Motivated by this, we propose Barlow Graph Auto-Encoder, a simple yet effective architecture for learning network embedding.
no code implementations • 9 Aug 2021 • Rayyan Ahmad Khan, Martin Kleinsteuber
HIN embedding has emerged as a promising research field for network analysis as it enables downstream tasks such as clustering and node classification.
1 code implementation • 11 Jan 2021 • Rayyan Ahmad Khan, Muhammad Umer Anwaar, Omran Kaddah, Martin Kleinsteuber
In this paper, we study how to simultaneously learn two highly correlated tasks of graph analysis, i. e., community detection and node representation learning.
no code implementations • 1 Jan 2021 • Rayyan Ahmad Khan, Muhammad Umer Anwaar, Omran Kaddah, Martin Kleinsteuber
In this paper, we study how to simultaneously learn two highly correlated tasks of graph analysis, i. e., community detection and node representation learning.
1 code implementation • 22 Oct 2020 • Muhammad Umer Anwaar, Zhiwei Han, Shyam Arumugaswamy, Rayyan Ahmad Khan, Thomas Weber, Tianming Qiu, Hao Shen, Yuanting Liu, Martin Kleinsteuber
In this paper, we employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs, which explicitly capture sequential semantics in graph structures.
Ranked #1 on Link Prediction on MovieLens 25M
1 code implementation • 19 Jun 2020 • Muhammad Umer Anwaar, Egor Labintcev, Martin Kleinsteuber
In this paper, we investigate the problem of retrieving images from a database based on a multi-modal (image-text) query.
Ranked #1 on Image Retrieval with Multi-Modal Query on FashionIQ
1 code implementation • 3 Apr 2020 • Rayyan Ahmad Khan, Muhammad Umer Anwaar, Martin Kleinsteuber
Variational autoencoder (VAE) is a widely used generative model for learning latent representations.
1 code implementation • 24 Jul 2019 • Muhammad Umer Anwaar, Dmytro Rybalko, Martin Kleinsteuber
In the literature, it is proposed to employ user feedback (such as clicks, add-to-basket (AtB) clicks and orders) to generate relevance judgments.
no code implementations • 8 Oct 2018 • Xian Wei, Hao Shen, Martin Kleinsteuber
We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i. e., sparse representation and the trace quotient criterion.
no code implementations • 12 Mar 2018 • Rayyan Ahmad Khan, Rana Ali Amjad, Martin Kleinsteuber
We propose a new clustering algorithm, Extended Affinity Propagation, based on pairwise similarities.
no code implementations • 1 Aug 2017 • Martin Kiechle, Martin Storath, Andreas Weinmann, Martin Kleinsteuber
We note that the features can be learned from a small set of images, from a single image, or even from image patches.
no code implementations • 14 Jun 2017 • Alexander Sagel, Martin Kleinsteuber
Recent research in image and video recognition indicates that many visual processes can be thought of as being generated by a time-varying generative model.
no code implementations • 19 Aug 2016 • Hiroyuki Kasai, Wolfgang Kellerer, Martin Kleinsteuber
This problem is cast as a low-rank subspace tracking problem for normal flows under incomplete observations, and an outlier detection problem for abnormal flows.
no code implementations • CVPR 2016 • Xian Wei, Hao Shen, Martin Kleinsteuber
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner.
no code implementations • 12 Jun 2015 • Clemens Hage, Martin Kleinsteuber
Over the past years Robust PCA has been established as a standard tool for reliable low-rank approximation of matrices in the presence of outliers.
no code implementations • 9 Mar 2015 • Matthias Seibert, Julian Wörmann, Rémi Gribonval, Martin Kleinsteuber
In many applications, it is also required that the filter responses are obtained in a timely manner, which can be achieved by filters with a separable structure.
no code implementations • 25 Jun 2014 • Martin Kiechle, Tim Habigt, Simon Hawe, Martin Kleinsteuber
In this paper, we propose a co-sparse analysis model that is able to capture the interdependency of two image modalities.
no code implementations • 6 Jun 2014 • Matthias Seibert, Julian Wörmann, Rémi Gribonval, Martin Kleinsteuber
The ability of having a sparse representation for a certain class of signals has many applications in data analysis, image processing, and other research fields.
no code implementations • 20 Mar 2014 • Matthias Seibert, Martin Kleinsteuber, Rémi Gribonval, Rodolphe Jenatton, Francis Bach
The main goal of this paper is to provide a sample complexity estimate that controls to what extent the empirical average deviates from the cost function.
no code implementations • 19 Dec 2013 • Xian Wei, Hao Shen, Martin Kleinsteuber
Video representation is an important and challenging task in the computer vision community.
no code implementations • 17 Dec 2013 • Claudia Nieuwenhuis, Daniel Cremers, Simon Hawe, Martin Kleinsteuber
We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation within a convex multilabel optimization framework.
no code implementations • 13 Dec 2013 • Rémi Gribonval, Rodolphe Jenatton, Francis Bach, Martin Kleinsteuber, Matthias Seibert
Many modern tools in machine learning and signal processing, such as sparse dictionary learning, principal component analysis (PCA), non-negative matrix factorization (NMF), $K$-means clustering, etc., rely on the factorization of a matrix obtained by concatenating high-dimensional vectors from a training collection.
no code implementations • CVPR 2013 • Simon Hawe, Matthias Seibert, Martin Kleinsteuber
Many techniques in computer vision, machine learning, and statistics rely on the fact that a signal of interest admits a sparse representation over some dictionary.
no code implementations • 19 Apr 2013 • Martin Kiechle, Simon Hawe, Martin Kleinsteuber
High-resolution depth maps can be inferred from low-resolution depth measurements and an additional high-resolution intensity image of the same scene.
no code implementations • 8 Feb 2013 • Florian Seidel, Clemens Hage, Martin Kleinsteuber
An increasing number of methods for background subtraction use Robust PCA to identify sparse foreground objects.
no code implementations • 2 Oct 2012 • Clemens Hage, Martin Kleinsteuber
Many applications in data analysis rely on the decomposition of a data matrix into a low-rank and a sparse component.
no code implementations • 24 Apr 2012 • Simon Hawe, Martin Kleinsteuber, Klaus Diepold
Our method is based on an $\ell_p$-norm minimization on the set of full rank matrices with normalized columns.