Projects
Multi-modal transfer learning through self-supervision for real-time venue mapping. University of Antwerp
Representation Learning with Restricted Kernel Machines KU Leuven
In this thesis, we extend the use of Restricted Kernel Machines (RKM) to combine the advantages of classical mathematical methods with deep learning models to solve problems in various domains, including generative modeling, disentangled representation learning, robust representation learning, and time-series forecasting. Our work builds on the framework of multi-view kernel principal component analysis and extends it to learn a common ...
Model-based image computing for multi-X medical image data. KU Leuven
Latent Variable Models for Language and Image Understanding in Social Media and E-Commerce Data KU Leuven
More content has been created in the past few years than in the entire history of humankind. With the exponential growth of user-contributed content, it becomes increasingly important to develop systems capable to intelligently process both language and images.
While understanding language appears effortless for humans from a young age, for computers, this is quite a challenging task. Inherently, languages are ambiguous and rich. Many ...
SRP-Onderzoekszwaartepunt: Learning-based Signal and Data Processing Systems (LSDS) Vrije Universiteit Brussel
Weakly supervised machine learning algorithms for object recognition in-the-wild and entity linking in videos KU Leuven
With the proliferation of video-rich data on the Internet, there is a pressing need for search tools that can retrieve not only relevant videos from a corpus, but also relevant snippets within a video. For retrieving relevant videos, current search technologies hinge on labor-intensive manual annotation of tags, which are subjective and often incomplete. To fully automate search and retrieval systems, we need tools that can understand the ...
MAChine Communication with Humans and Inference in NAtural environments (MACCHINA) KU Leuven
Exploring Unsupervised Learning for Computer Vision Tasks with Neural Networks KU Leuven
Traditional supervised learning algorithms for computer vision tasks usually rely on large extensively annotated datasets. However, this labeling process can be expensive, biased, and susceptible to ambiguity.
The thesis explores self-supervised or unsupervised learning as a viable alternative to overcome these obstacles.
Specifically, it tackles fundamental perception tasks via neural networks and aims to automatically discover ...
Cross-lingual and Cross-modal Fashion Product Linking ans Search KU Leuven
The internet has dramatically changed the way people buy and sell products. It has caused a shift from physical to digital retail, which has only been accelerated by the recent COVID-19 pandemic. What attracts people to online shopping is the wider selection, better prices, and the convenience of shopping anywhere, anytime. However, online customers can also easily be overwhelmed by the wide range of products which can sometimes hinder them ...