|
Sergi Garcia Bordils, George Tom, Sangeeth Reddy, Minesh Mathew, Marçal Rusiñol, C.V. Jawahar, et al. (2022). Read While You Drive-Multilingual Text Tracking on the Road. In 15th IAPR International workshop on document analysis systems (Vol. 13237, 756–770). LNCS.
Abstract: Visual data obtained during driving scenarios usually contain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully annotated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods exploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.
|
|
|
Ruben Tito, Dimosthenis Karatzas, & Ernest Valveny. (2023). Hierarchical multimodal transformers for Multi-Page DocVQA. PR - Pattern Recognition, 144, 109834.
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.
|
|
|
Sergi Garcia Bordils, Andres Mafla, Ali Furkan Biten, Oren Nuriel, Aviad Aberdam, Shai Mazor, et al. (2022). Out-of-Vocabulary Challenge Report. In Proceedings European Conference on Computer Vision Workshops (Vol. 13804, 359–375). LNCS.
Abstract: This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions.
|
|
|
Ali Furkan Biten, Andres Mafla, Lluis Gomez, & Dimosthenis Karatzas. (2022). Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching. In Winter Conference on Applications of Computer Vision (pp. 1391–1400).
Abstract: The task of image-text matching aims to map representations from different modalities into a common joint visual-textual embedding. However, the most widely used datasets for this task, MSCOCO and Flickr30K, are actually image captioning datasets that offer a very limited set of relationships between images and sentences in their ground-truth annotations. This limited ground truth information forces us to use evaluation metrics based on binary relevance: given a sentence query we consider only one image as relevant. However, many other relevant images or captions may be present in the dataset. In this work, we propose two metrics that evaluate the degree of semantic relevance of retrieved items, independently of their annotated binary relevance. Additionally, we incorporate a novel strategy that uses an image captioning metric, CIDEr, to define a Semantic Adaptive Margin (SAM) to be optimized in a standard triplet loss. By incorporating our formulation to existing models, a large improvement is obtained in scenarios where available training data is limited. We also demonstrate that the performance on the annotated image-caption pairs is maintained while improving on other non-annotated relevant items when employing the full training set. The code for our new metric can be found at github. com/furkanbiten/ncsmetric and the model implementation at github. com/andrespmd/semanticadaptive_margin.
Keywords: Measurement; Training; Integrated circuits; Annotations; Semantics; Training data; Semisupervised learning
|
|
|
Ali Furkan Biten, Lluis Gomez, & Dimosthenis Karatzas. (2022). Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning. In Winter Conference on Applications of Computer Vision (pp. 1381–1390).
Abstract: Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase
in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models’ object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights are available online.
Keywords: Measurement; Training; Visualization; Analytical models; Computer vision; Computational modeling; Training data
|
|
|
Minesh Mathew, Viraj Bagal, Ruben Tito, Dimosthenis Karatzas, Ernest Valveny, & C.V. Jawahar. (2022). InfographicVQA. In Winter Conference on Applications of Computer Vision (pp. 1697–1706).
Abstract: Infographics communicate information using a combination of textual, graphical and visual elements. This work explores the automatic understanding of infographic images by using a Visual Question Answering technique. To this end, we present InfographicVQA, a new dataset comprising a diverse collection of infographics and question-answer annotations. The questions require methods that jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with an emphasis on questions that require elementary reasoning and basic arithmetic skills. For VQA on the dataset, we evaluate two Transformer-based strong baselines. Both the baselines yield unsatisfactory results compared to near perfect human performance on the dataset. The results suggest that VQA on infographics--images that are designed to communicate information quickly and clearly to human brain--is ideal for benchmarking machine understanding of complex document images. The dataset is available for download at docvqa. org
Keywords: Document Analysis Datasets; Evaluation and Comparison of Vision Algorithms; Vision and Languages
|
|
|
Anjan Dutta, & Zeynep Akata. (2019). Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 5089–5098).
Abstract: Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains a cycle consistency that only requires supervision at category levels, and avoids the need of highly-priced aligned sketch-image pairs. A classification criteria on the generators' outputs ensures the visual to semantic space mapping to be discriminating. Furthermore, we propose to combine textual and hierarchical side information via a feature selection auto-encoder that selects discriminating side information within a same end-to-end model. Our results demonstrate a significant boost in zero-shot SBIR performance over the state-of-the-art on the challenging Sketchy and TU-Berlin datasets.
|
|
|
Jialuo Chen, M.A.Souibgui, Alicia Fornes, & Beata Megyesi. (2020). A Web-based Interactive Transcription Tool for Encrypted Manuscripts. In 3rd International Conference on Historical Cryptology (pp. 52–59).
Abstract: Manual transcription of handwritten text is a time consuming task. In the case of encrypted manuscripts, the recognition is even more complex due to the huge variety of alphabets and symbol sets. To speed up and ease this process, we present a web-based tool aimed to (semi)-automatically transcribe the encrypted sources. The user uploads one or several images of the desired encrypted document(s) as input, and the system returns the transcription(s). This process is carried out in an interactive fashion with
the user to obtain more accurate results. For discovering and testing, the developed web tool is freely available.
|
|
|
Manuel Carbonell, Joan Mas, Mauricio Villegas, Alicia Fornes, & Josep Llados. (2019). End-to-End Handwritten Text Detection and Transcription in Full Pages. In 2nd International Workshop on Machine Learning (Vol. 5, pp. 29–34).
Abstract: When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect
the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume
segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
Keywords: Handwritten Text Recognition; Layout Analysis; Text segmentation; Deep Neural Networks; Multi-task learning
|
|
|
Manuel Carbonell, Alicia Fornes, Mauricio Villegas, & Josep Llados. (2020). A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages. PRL - Pattern Recognition Letters, 136, 219–227.
Abstract: In the last years, the consolidation of deep neural network architectures for information extraction in document images has brought big improvements in the performance of each of the tasks involved in this process, consisting of text localization, transcription, and named entity recognition. However, this process is traditionally performed with separate methods for each task. In this work we propose an end-to-end model that combines a one stage object detection network with branches for the recognition of text and named entities respectively in a way that shared features can be learned simultaneously from the training error of each of the tasks. By doing so the model jointly performs handwritten text detection, transcription, and named entity recognition at page level with a single feed forward step. We exhaustively evaluate our approach on different datasets, discussing its advantages and limitations compared to sequential approaches. The results show that the model is capable of benefiting from shared features by simultaneously solving interdependent tasks.
|
|
|
Pau Riba, Anjan Dutta, Lutz Goldmann, Alicia Fornes, Oriol Ramos Terrades, & Josep Llados. (2019). Table Detection in Invoice Documents by Graph Neural Networks. In 15th International Conference on Document Analysis and Recognition (pp. 122–127).
Abstract: Tabular structures in documents offer a complementary dimension to the raw textual data, representing logical or quantitative relationships among pieces of information. In digital mail room applications, where a large amount of
administrative documents must be processed with reasonable accuracy, the detection and interpretation of tables is crucial. Table recognition has gained interest in document image analysis, in particular in unconstrained formats (absence of rule lines, unknown information of rows and columns). In this work, we propose a graph-based approach for detecting tables in document images. Instead of using the raw content (recognized text), we make use of the location, context and content type, thus it is purely a structure perception approach, not dependent on the language and the quality of the text
reading. Our framework makes use of Graph Neural Networks (GNNs) in order to describe the local repetitive structural information of tables in invoice documents. Our proposed model has been experimentally validated in two invoice datasets and achieved encouraging results. Additionally, due to the scarcity
of benchmark datasets for this task, we have contributed to the community a novel dataset derived from the RVL-CDIP invoice data. It will be publicly released to facilitate future research.
|
|
|
Lei Kang, Pau Riba, Mauricio Villegas, Alicia Fornes, & Marçal Rusiñol. (2021). Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture. PR - Pattern Recognition, 112, 107790.
Abstract: Sequence-to-sequence models have recently become very popular for tackling
handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging
problem. The main challenge faced when training a language model is to
deal with the language model corpus which is usually different to the one
used for training the handwritten word recognition system. Thus, the bias
between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this
work, we introduce Candidate Fusion, a novel way to integrate an external
language model to a sequence-to-sequence architecture. Moreover, it provides suggestions from an external language knowledge, as a new input to
the sequence-to-sequence recognizer. Hence, Candidate Fusion provides two
improvements. On the one hand, the sequence-to-sequence recognizer has
the flexibility not only to combine the information from itself and the language model, but also to choose the importance of the information provided
by the language model. On the other hand, the external language model
has the ability to adapt itself to the training corpus and even learn the
most commonly errors produced from the recognizer. Finally, by conducting
comprehensive experiments, the Candidate Fusion proves to outperform the
state-of-the-art language models for handwritten word recognition tasks.
|
|
|
Asma Bensalah, Pau Riba, Alicia Fornes, & Josep Llados. (2019). Shoot less and Sketch more: An Efficient Sketch Classification via Joining Graph Neural Networks and Few-shot Learning. In 13th IAPR International Workshop on Graphics Recognition (pp. 80–85).
Abstract: With the emergence of the touchpad devices and drawing tablets, a new era of sketching started afresh. However, the recognition of sketches is still a tough task due to the variability of the drawing styles. Moreover, in some application scenarios there is few labelled data available for training,
which imposes a limitation for deep learning architectures. In addition, in many cases there is a need to generate models able to adapt to new classes. In order to cope with these limitations, we propose a method based on few-shot learning and graph neural networks for classifying sketches aiming for an efficient neural model. We test our approach with several databases of
sketches, showing promising results.
Keywords: Sketch classification; Convolutional Neural Network; Graph Neural Network; Few-shot learning
|
|
|
Albert Berenguel, Oriol Ramos Terrades, Josep Llados, & Cristina Cañero. (2019). Recurrent Comparator with attention models to detect counterfeit documents. In 15th International Conference on Document Analysis and Recognition.
Abstract: This paper is focused on the detection of counterfeit documents via the recurrent comparison of the security textured background regions of two images. The main contributions are twofold: first we apply and adapt a recurrent comparator architecture with attention mechanism to the counterfeit detection task, which constructs a representation of the background regions by recurrently condition the next observation, learning the difference between genuine and counterfeit images through iterative glimpses. Second we propose a new counterfeit document dataset to ensure the generalization of the learned model towards the detection of the lack of resolution during the counterfeit manufacturing. The presented network, outperforms state-of-the-art classification approaches for counterfeit detection as demonstrated in the evaluation.
|
|
|
Anjan Dutta, Pau Riba, Josep Llados, & Alicia Fornes. (2020). Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition. NEUCOMA - Neural Computing and Applications, 32, 11579–11596.
Abstract: Despite being very successful within the pattern recognition and machine learning community, graph-based methods are often unusable because of the lack of mathematical operations defined in graph domain. Graph embedding, which maps graphs to a vectorial space, has been proposed as a way to tackle these difficulties enabling the use of standard machine learning techniques. However, it is well known that graph embedding functions usually suffer from the loss of structural information. In this paper, we consider the hierarchical structure of a graph as a way to mitigate this loss of information. The hierarchical structure is constructed by topologically clustering the graph nodes and considering each cluster as a node in the upper hierarchical level. Once this hierarchical structure is constructed, we consider several configurations to define the mapping into a vector space given a classical graph embedding, in particular, we propose to make use of the stochastic graphlet embedding (SGE). Broadly speaking, SGE produces a distribution of uniformly sampled low-to-high-order graphlets as a way to embed graphs into the vector space. In what follows, the coarse-to-fine structure of a graph hierarchy and the statistics fetched by the SGE complements each other and includes important structural information with varied contexts. Altogether, these two techniques substantially cope with the usual information loss involved in graph embedding techniques, obtaining a more robust graph representation. This fact has been corroborated through a detailed experimental evaluation on various benchmark graph datasets, where we outperform the state-of-the-art methods.
|
|