89%Must read
?Must readVote to see the score
Handwritten Text Recognition Lives in the High-Pixel Variance Subspace
For handwritten text recognition, discriminative signals lie in high-variance pixel directions, so pixel-reconstruction self-supervised pretraining outperforms contrastive methods and achieves lower character error rates across benchmarks.
Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026
– ReadersNo votes yet
16/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 16 of 20 reviewers recommend it
lenient 4/5
medium 9/10
strict 3/5