15 citations · 18 across the 6 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 1 cited
SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Martin Kišš, Michal Hradiš, Karel Beneš +2
This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function $\unicode{x…
cs.CV2022★ 1 cited
Importance of Textlines in Historical Document Classification
Martin Kišš, Jan Kohút, Karel Beneš +1
This paper describes a system prepared at Brno University of Technology for ICDAR 2021 Competition on Historical Document Classification, experiments leading to its design, and the…