Pith. sign in

REVIEW 1 cited by

Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.05909 v3 pith:KFYPPIWR submitted 2021-10-12 cs.CV

classification cs.CV
keywords approachesmodeldatadecodingduringencodergithubmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In contrast to Connectionist Temporal Classification (CTC) approaches, Sequence-To-Sequence (S2S) models for Handwritten Text Recognition (HTR) suffer from errors such as skipped or repeated words which often occur at the end of a sequence. In this paper, to combine the best of both approaches, we propose to use the CTC-Prefix-Score during S2S decoding. Hereby, during beam search, paths that are invalid according to the CTC confidence matrix are penalised. Our network architecture is composed of a Convolutional Neural Network (CNN) as visual backbone, bidirectional Long-Short-Term-Memory-Cells (LSTMs) as encoder, and a decoder which is a Transformer with inserted mutual attention layers. The CTC confidences are computed on the encoder while the Transformer is only used for character-wise S2S decoding. We evaluate this setup on three HTR data sets: IAM, Rimes, and StAZH. On IAM, we achieve a competitive Character Error Rate (CER) of 2.95% when pretraining our model on synthetic data and including a character-based language model for contemporary English. Compared to other state-of-the-art approaches, our model requires about 10-20 times less parameters. Access our shared implementations via this link to GitHub: https://github.com/Planet-AI-GmbH/tfaip-hybrid-ctc-s2s.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Comparing GAN, diffusion, and autoregressive handwriting generators shows the autoregressive model helps recognition most with very little real data, while the diffusion model wins once more real data is available.

Pith tools