Papers › End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network

End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network

7 Dec 2020arXiv:2012.03868archive 2025-07-28

Denis Coquenet, Clément Chatelain, Thierry Paquet

Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

FactoDeepLearning/VerticalAttentionOCR officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderHandwritten Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Text Recognition IAM VAN CER 4.32 #7 of 17 Archive leaderboard report
Handwritten Text Recognition IAM VAN WER 16.24 #7 of 17 Archive leaderboard report
Handwritten Text Recognition IAM(line-level) VAN Test CER 5.0 #3 of 5 Archive leaderboard report
Handwritten Text Recognition IAM(line-level) VAN Test WER 16.3 #3 of 5 Archive leaderboard report
Handwritten Text Recognition READ2016(line-level) VAN Test CER 4.1 #2 of 5 Archive leaderboard report
Handwritten Text Recognition READ2016(line-level) VAN Test WER 16.3 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections