Related papers: Which tone-mapping operator is the best? A compara…
Machine Translation (MT) has developed rapidly since the release of Large Language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores from human-labeled data.…
Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels. The many approaches to labelling scenes can be divided into two clear groups: view-based…
We propose a self-supervised shared encoder model that achieves strong results on several visual, language and multimodal benchmarks while being data, memory and run-time efficient. We make three key contributions. First, in contrast to…
Wireless-based activity sensing has gained significant attention due to its wide range of applications. We investigate radio-based multi-class classification of human activities using massive multiple-input multiple-output (MIMO) channel…
Mapping is an important part of many robotic applications. In order to measure the performance of the mapping process we have to measure the quality of its result: the map. The map is essential for robotic algorithms like localization and…
How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-down manner, to direct…
Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and…
To support cooperative perception (CP) of networked mobile agents in dynamic scenarios, the efficient and robust transmission of sensory data is a critical challenge. Deep learning-based joint source-channel coding (JSCC) has demonstrated…
Safe and efficient robot operation in complex human environments can benefit from good models of site-specific motion patterns. Maps of Dynamics (MoDs) provide such models by encoding statistical motion patterns in a map, but existing…
Text-to-image diffusion has attracted vast attention due to its impressive image-generation capabilities. However, when it comes to human-centric text-to-image generation, particularly in the context of faces and hands, the results often…
In the paper, we propose a novel methodology to map learning algorithms on data (performance map) in order to gain more insights in the distribution of their performances across their parameter space. This methodology provides useful…
Running numerous experiments in simulation is a necessary step before deploying a control system on a real robot. In this paper we introduce a novel benchmark that is aimed at quantitatively evaluating the quality of vision-based…
Feature-based visual structure and motion reconstruction pipelines, common in visual odometry and large-scale reconstruction from photos, use the location of corresponding features in different images to determine the 3D structure of the…
Real-world imaging systems acquire measurements that are degraded by noise, optical aberrations, and other imperfections that make image processing for human viewing and higher-level perception tasks challenging. Conventional cameras…
Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from…
Video Foundation Models (VFMs) exhibit remarkable visual generation performance, but struggle in compositional scenarios (e.g., motion, numeracy, and spatial relation). In this work, we introduce Test-Time Optimization and Memorization…
Emotional information is essential for enhancing human-computer interaction and deepening image understanding. However, while deep learning has advanced image recognition, the intuitive understanding and precise control of emotional…
Quantum tomography is a process of quantum state reconstruction using data from multiple measurements. An essential goal for a quantum tomography algorithm is to find measurements that will maximize the useful information about an unknown…
Atom probe tomography is often introduced as providing "atomic-scale" mapping of the composition of materials and as such is often exploited to analyse atomic neighbourhoods within a material. Yet quantifying the actual spatial performance…
Multidimensional projections (MP) are among the most essential approaches in the visual analysis of multidimensional data. It transforms multidimensional data into two-dimensional representations that may be shown as scatter plots while…