Kenji Kawashima

Papers that credit Kenji Kawashima in their source bylines. Matching names may refer to different researchers.

1 results

1. PaperComputer Vision

   Medical captions can give segmentation models lesion size

   A caption audit finds that lesion-size clues explain much of the measured text gain in tested colonoscopy segmentation models.

   Added to Chiosa Nov 12, 2026