Abstract: Despite the latest advances in Deep Learning, the recognition of handwritten music scores is still a challenging endeavour. Even though the recent Sequence to Sequence(Seq2Seq) architectures have demonstrated its capacity to reliably recognise handwritten text, their performance is still far from satisfactory when applied to historical handwritten scores. Indeed, the ambiguous nature of handwriting, the non-standard musical notation employed by composers of the time and the decaying state of old paper make these scores remarkably difficult to read, sometimes even by trained humans. Thus, in this work we explore the incorporation of language models into a Seq2Seq-based architecture to try to improve transcriptions where the aforementioned unclear writing produces statistically unsound mistakes, which as far as we know, has never been attempted for this field of research on this architecture. After studying various Language Model integration techniques, the experimental evaluation on historical handwritten music scores shows a significant improvement over the state of the art, showing that this is a promising research direction for dealing with such difficult manuscripts.

Abstract: Many historical manuscripts that hold trustworthy memories of the past societies contain information organized in a structured layout (e.g. census, birth or marriage records). The precious information stored in these documents cannot be effectively used nor accessed without costly annotation efforts. The transcription driven by the semantic categories of words is crucial for the subsequent access. In this paper we describe an approach to extract information from structured historical handwritten text images and build a knowledge representation for the extraction of meaning out of historical data. The method extracts information, such as named entities, without the need of an intermediate transcription step, thanks to the incorporation of context information through language models. Our system has two variants, the first one is based on bigrams, whereas the second one is based on recurrent neural networks. Concretely, our second architecture integrates a Convolutional Neural Network to model visual information from word images together with a Bidirecitonal Long Short Term Memory network to model the relation among the words. This integrated sequential approach is able to extract more information than just the semantic category (e.g. a semantic category can be associated to a person in a record). Our system is generic, it deals with out-of-vocabulary words by design, and it can be applied to structured handwritten texts from different domains. The method has been validated with the ICDAR IEHHR competition protocol, outperforming the existing approaches.

Abstract: Handwriting recognition consists in obtaining the transcription of a text image. Recent word spotting methods based on attribute embedding have shown good performance when recognizing words. However, they are holistic methods in the sense that they recognize the word as a whole (i.e. they find the closest word in the lexicon to the word image). Consequently,
these kinds of approaches are not able to deal with out of vocabulary words, which are common in historical manuscripts. Also, they cannot be extended to recognize text lines. In order to address these issues, in this paper we propose a handwriting recognition method that adapts the attribute embedding to sequence learning. Concretely, the method learns the attribute embedding of patches of word images with a convolutional neural network. Then, these embeddings are presented as a sequence to a recurrent neural network that produces the transcription. We obtain promising results even without the use of any kind of dictionary or language model

Abstract: Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.

Abstract: In this report, we present the final results of the ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. The RoadText challenge is based on the RoadText-1K dataset and aims to assess and enhance current methods for scene text detection, recognition, and tracking in videos. The RoadText-1K dataset contains 1000 dash cam videos with annotations for text bounding boxes and transcriptions in every frame. The competition features an end-to-end task, requiring systems to accurately detect, track, and recognize text in dash cam videos. The paper presents a comprehensive review of the submitted methods along with a detailed analysis of the results obtained by the methods. The analysis provides valuable insights into the current capabilities and limitations of video text detection, tracking, and recognition systems for dashcam videos.