-
learning has strong potential for computer vision, from hyperbolic image segmentation [2] to hyperbolic tree embeddings [3] and hyperbolic vision-language models [4,5]. [1] Nickel, Maximillian, and Douwe
-
geometry altogether and operate in hyperbolic space. Our lab has published multiple papers showing that hyperbolic deep learning has strong potential for computer vision, from hyperbolic image segmentation
-
to advance 3D imaging methods for neuroscience. Your colleagues: An interdisciplinary team working across the Cognitive Neuroscience Department and the Mental Health and Neuroscience Research Institute
-
. Besides this, you will work on scene understanding using RGB and possibly thermal and radar images, including based on object detection and image segmentation, and collaborate effectively with other
-
for non-invasive brain imaging techniques such as fNIRS or fMRI. With the constantly improving spatial resolution of these methods, a thorough knowledge of potential differences in vascular architecture
-
will work on scene understanding using RGB and possibly thermal and radar images, including based on object detection and image segmentation, and collaborate effectively with other technical partners who
-
for an ambitious PhD student on perceptual foundation models. Your research is part of the Video & Image Sense Lab. Join our team! Recent breakthroughs in Artificial Intelligence resulted in the emergence
-
with colleagues with diverse backgrounds? The Informatics Institute is looking for an ambitious PhD student on perceptual foundation models. Your research is part of the Video & Image Sense Lab. Join our
-
readiness of these smart materials is still low, which makes their integration in a smart material system with various segments a challenging design assignment. Therefore, it needs elaborative testing and
-
other viruses, including the coronaviruses, using the latest imaging techniques to track how they replicate. He is also investigating the ‘arms race’ between the virus and the host’s immune system, how