Applying video instance segmentation with COCO-pretrained weights improves linking of buildings across historical Siegfried maps, but the proposed synthetic-video self-supervised pretraining adds no measurable gain over standard COCO image pretraining.
Schwing, Alexander Kirillov, and Rohit Gird- har
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
Applying video instance segmentation with COCO-pretrained weights improves linking of buildings across historical Siegfried maps, but the proposed synthetic-video self-supervised pretraining adds no measurable gain over standard COCO image pretraining.