Zobrazeno 1 - 10
of 7 281
pro vyhledávání: '"A, Kuijper"'
Autor:
Knauthe, Volker, Rak, Arne, Wirth, Tristan, Pöllabauer, Thomas, Metzler, Simon, Kuijper, Arjan, Fellner, Dieter W.
Semantic Image Segmentation facilitates a multitude of real-world applications ranging from autonomous driving over industrial process supervision to vision aids for human beings. These models are usually trained in a supervised fashion using example
Externí odkaz:
http://arxiv.org/abs/2405.12864
Autor:
Knauthe, Volker, Weitz, Paul, Pöllabauer, Thomas, Wirth, Tristan, Rak, Arne, Kuijper, Arjan, Fellner, Dieter W.
Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e.g., in the healthcare domain and dangerous environments. While the general usability of these techniques is high, there are stil
Externí odkaz:
http://arxiv.org/abs/2405.12861
Deep Neural Networks (DNNs) require large amounts of annotated training data for a good performance. Often this data is generated using manual labeling (error-prone and time-consuming) or rendering (requiring geometry and material information). Both
Externí odkaz:
http://arxiv.org/abs/2405.07653
We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation. This two-phase algorithm initially employs the Lempel-Ziv-Welch (LZW) algorithm to construct a dictionary f
Externí odkaz:
http://arxiv.org/abs/2405.01584
Publikováno v:
21st Eurographics Workshop on Graphics and Cultural Heritage (GCH 2023)
Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic sketches. O
Externí odkaz:
http://arxiv.org/abs/2402.08310
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods for directly regressing poses from RGB images using dense features have achieved state-of-the-art results. Stereo vision, which prov
Externí odkaz:
http://arxiv.org/abs/2402.05610
Autor:
de Kuijper, Kees, Diwan, Rishank, Pal, Partha Sarathi, Ritter, Andreas, Parkinson, Pablo M. Saz, Kong, Andy C. T., Parker, Quentin A.
Publikováno v:
Exp Astron 57, 16 (2024)
The low-energy $\gamma$-ray (0.1-30 MeV) sky has been relatively unexplored since the decommissioning of the COMPTEL instrument on the Compton Gamma-Ray Observatory (CGRO) satellite in 2000. However, the study of this part of the energy spectrum (the
Externí odkaz:
http://arxiv.org/abs/2401.09735
In safety-critical domains such as autonomous driving and medical diagnosis, the reliability of machine learning models is crucial. One significant challenge to reliability is concept drift, which can cause model deterioration over time. Traditionall
Externí odkaz:
http://arxiv.org/abs/2311.13374
In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises. The working principle was based on the ultrasound Doppler sensing with the device built-in hardware. Appl
Externí odkaz:
http://arxiv.org/abs/2311.11910
Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known and sensiti
Externí odkaz:
http://arxiv.org/abs/2311.03970