activity
20242026
most citedBigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.CV2025

Another BRIXEL in the Wall: Towards Cheaper Dense Features

Alexander Lappe, Martin A. Giese

Vision foundation models achieve strong performance on both global and locally dense downstream tasks. Pretrained on large images, the recent DINOv3 model family is able to produce…

cs.CV2025

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs

Alexander Lappe, Martin A. Giese

Recent work has shown that the attention maps of the widely popular DINOv2 model exhibit artifacts, which hurt both model interpretability and performance on dense image tasks. The…