Related papers: A Web-Based Resource Model for eScience: Object Re…
In recent years, a variety of digital repository and archival systems have been developed and adopted. All of these systems aim at hosting a variety of compound digital assets and at providing tools for storing, managing and accessing those…
This paper presents a novel structured knowledge representation called the functional object-oriented network (FOON) to model the connectivity of the functional-related objects and their motions in manipulation tasks. The graphical model…
Scientists strive to make their datasets available in open repositories, with the goal that they be findable, accessible, interoperable, and reusable (FAIR). Although it is hard for most investigators to remember all the guiding principles…
With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, where crucial factors…
In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object…
This paper introduces a no-code, machine-readable documentation framework for open datasets, with a focus on responsible AI (RAI) considerations. The framework aims to improve comprehensibility, and usability of open datasets, facilitating…
Web information extraction (WIE) is the task of automatically extracting data from web pages, offering high utility for various applications. The evaluation of WIE systems has traditionally relied on benchmarks built from HTML snapshots…
We present HOReeNet, which tackles the novel task of manipulating images involving hands, objects, and their interactions. Especially, we are interested in transferring objects of source images to target images and manipulating 3D hand…
Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones,…
Motivation. Digital commons is an emerging phenomenon and of increasing importance, as we enter a digital society. Open data is one example that makes up a pivotal input and foundation for many of today's digital services and applications.…
Robotic bin packing aids in a wide range of real-world scenarios such as e-commerce and warehouses. Yet, existing works focus mainly on considering the shape of objects to optimize packing compactness and neglect object properties such as…
Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural considerations. Therefore, understanding the composition…
Research Objects (ROs) are semantically enhanced aggregations of resources associated to scientific experiments, such as data, provenance of these data, the scientific workflow used to run the experiment, intermediate results, logs and the…
The problem that the same information need can be expressed in a variety of ways is especially true for scientific literature. Each scientific discipline has its own domain-specific language and vocabulary. This language is coded into…
Learning effective multi-modal 3D representations of objects is essential for numerous applications, such as augmented reality and robotics. Existing methods often rely on task-specific embeddings that are tailored either for semantic…
Modern technologies are enabling scientists to collect extraordinary amounts of complex and sophisticated data across a huge range of scales like never before. With this onslaught of data, we can allow the focal point to shift towards…
The European Open Science Cloud (EOSC) is in its early stages, but already some aspects of the EOSC vision are starting to become reality, for example the EOSC portal and the development of metadata catalogues. In the astrophysical domain…
The prevailing model for disseminating scientific knowledge relies on individual publications dispersed across numerous journals and archives. This legacy system is ill suited to the recent exponential proliferation of publications,…
In this paper we present a model based on the principles of Linked Data that can be used to describe the interrelationships of images, texts and other resources to facilitate the interoperability of repositories of medieval manuscripts or…
The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to…