Zu vergebende Abschlussarbeiten

• Masked autoencoding as pre-training for traffic participant detection
• Contrastive learning for tracking traffic participants in bird’s-eye view videos

Veröffentlichungen

Royden Wagner, Karl Rohr. CellCentroidFormer: Combining Self-attention and Convolution for Cell Detection. In Medical Image Understanding and Analysis, 2022.

Royden Wagner, Karl Rohr. EfficientCellSeg: Efficient Volumetric Cell Segmentation Using Context Aware Pseudocoloring. In Medical Imaging with Deep Learning, 2022.

Jonas Dann, Royden Wagner, Daniel Ritter, Christian Faerber, Holger Froening. PipeJSON: Parsing JSON at Line Speed on FPGAs. In Data Management on New Hardware, 2022.