151 citations · 303 across the 17 of their papers we have counts for
Showing 2026 · cs.CVShow all
2 papers · 2 filters
cs.CV2026
Cytoarchitecture in Words: Weakly Supervised Vision-Language Modeling for Human Brain Microscopy
Matthew Sutton, Katrin Amunts, Timo Dickscheid +1
Vision foundation models increasingly support interactive scientific workflows, but natural-language interaction requires coupling visual representations to language. Curated image…
cs.CV2026
Depth-Wise Representation Development Under Blockwise Self-Supervised Learning for Video Vision Transformers
Jonas Römer, Timo Dickscheid
End-to-end backpropagation couples all layers through a global error signal, enabling coordinated learning but requiring long-range credit assignment. Motivated by recent progress…