Character-based handwritten text transcription with attention networks

Poulos, Jason; Valle, Rafael F.

doi:10.1007/s00521-021-05813-1

Cited by 20 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An LSTM‐based GAN is proposed in Reference 26 to generate music data that sounds good. Hybrid (attentional) RNN and convolutional NN architectures have also been used for the problem of transcribing sequences of handwritten text in images 67 . In References 37,41,68–70 hybrid models are utilized to predict the trajectories of the vehicle or the vehicles in surrounding environments.…”

Section: Background and Related Workmentioning

confidence: 99%

Deep generative models for vehicle speed trajectories

Behnia,

Karbowski,

Sokolov

2023

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Generating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self‐driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed‐forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Deep generative models for vehicle speed trajectories

Behnia,

Karbowski,

Sokolov

2023

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

show abstract

“…Contrary to the CRNN-CTC architecture, attention-based models learn to align image pixels with the target sequence. As a result, the network learns to focus on a small relevant part of the feature vector to predict each token [19,22]. Another strength of this architecture is that the recurrent decoder learns an implicit language model at character-level.…”

Section: Handwriting Recognitionmentioning

confidence: 99%

“…It recently gained popularity for speech recognition, image captioning and neural translation [3,8,29]. The architecture has since been adapted for HTR [19,22], as illustrated in Fig. 2.…”

Section: The Attention-based Seq2seq Architecturementioning

confidence: 99%

A Comparative Study of Information Extraction Strategies Using an Attention-Based Neural Network

Tarride

Lemaitre

Coüasnon

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This article focuses on information extraction in historical handwritten marriage records. Traditional approaches rely on a sequential pipeline of two consecutive tasks: handwriting recognition is applied before named entity recognition. More recently, joint approaches that handle both tasks at the same time have been investigated, yielding state-of-the-art results. However, as these approaches have been used in different experimental conditions, they have not been fairly compared yet. In this work, we conduct a comparative study of sequential and joint approaches based on the same attention-based architecture, in order to quantify the gain that can be attributed to the joint learning strategy. We also investigate three new joint learning configurations based on multi-task or multi-scale learning. Our study shows that relying on a joint learning strategy can lead to an 8% increase of the complete recognition score. We also highlight the interest of multi-task learning and demonstrate the benefit of attention-based networks for information extraction. Our work achieves state-of-the-art performance in the ICDAR 2017 Information Extraction competition on the Esposalles database at line-level, without any language modelling or post-processing.

show abstract

“…The NN architecture based on convolutional and 1D-LSTM layers is able to learn similar features with a significantly smaller computational cost [45]. Some notable state-of-the-art systems are only made up of CNN layers or attention techniques without any recurrent layer [13,42,43,44,52,57,58].…”

Section: Related Workmentioning

confidence: 99%

Lexicon and attention based handwritten text recognition system

Kumari

Singh²,

Rathore³

et al. 2022

MG&V

View full text Add to dashboard Cite

The handwritten text recognition problem is widely studied by the researchers of computer vision community due to its scope of improvement and applicability to daily lives. It is a sub-domain of pattern recognition. Due to advancement of computational power of computers since last few decades neural networks based systems heavily contributed towards providing the state-of-the-art handwritten text recognizers. In the same direction, we have taken two state-of-the art neural networks systems and merged the attention mechanism with it. The attention technique has been widely used in the domain of neural machine translations and automatic speech recognition and now is being implemented in text recognition domain. In this study, we are able to achieve 4.15% character error rate and 9.72% word error rate on IAM dataset, 7.07% character error rate and 16.14% word error rate on GW dataset after merging the attention and word beam search decoder with existing Flor et al. architecture. To analyse further, we have also used system similar to Shi et al. neural network system with greedy decoder and observed 23.27% improvement in character error rate from the base model.

show abstract

Character-based handwritten text transcription with attention networks

Cited by 20 publications

References 47 publications

Deep generative models for vehicle speed trajectories

Deep generative models for vehicle speed trajectories

A Comparative Study of Information Extraction Strategies Using an Attention-Based Neural Network

Lexicon and attention based handwritten text recognition system

Contact Info

Product

Resources

About