|
|
Raul Gomez, Jaume Gibert, Lluis Gomez and Dimosthenis Karatzas. 2020. Exploring Hate Speech Detection in Multimodal Publications. IEEE Winter Conference on Applications of Computer Vision.
Abstract: In this work we target the problem of hate speech detection in multimodal publications formed by a text and an image. We gather and annotate a large scale dataset from Twitter, MMHS150K, and propose different models that jointly analyze textual and visual information for hate speech detection, comparing them with unimodal detection. We provide quantitative and qualitative results and analyze the challenges of the proposed task. We find that, even though images are useful for the hate speech detection task, current multimodal models cannot outperform models analyzing only text. We discuss why and open the field and the dataset for further research.
|
|
|
|
David Fernandez, R.Manmatha, Josep Llados and Alicia Fornes. 2014. Sequential Word Spotting in Historical Handwritten Documents. 11th IAPR International Workshop on Document Analysis and Systems.101–105.
Abstract: In this work we present a handwritten word spotting approach that takes advantage of the a priori known order of appearance of the query words. Given an ordered sequence of query word instances, the proposed approach performs a
sequence alignment with the words in the target collection. Although the alignment is quite sparse, i.e. the number of words in the database is higher than the query set, the improvement in the overall performance is sensitively higher than isolated word spotting. As application dataset, we use a collection of handwritten marriage licenses taking advantage of the ordered
index pages of family names.
|
|
|
|
Sounak Dey, Anjan Dutta, Suman Ghosh, Ernest Valveny, Josep Llados and Umapada Pal. 2018. Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch. 24th International Conference on Pattern Recognition.916–921.
Abstract: In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best in both single and multiple object image retrieval in standard datasets.
|
|
|
|
Mohamed Ali Souibgui. 2022. Document Image Enhancement and Recognition in Low Resource Scenarios: Application to Ciphers and Handwritten Text. (Ph.D. thesis, IMPRIMA.)
Abstract: In this thesis, we propose different contributions with the goal of enhancing and recognizing historical handwritten document images, especially the ones with rare scripts, such as cipher documents.
In the first part, some effective end-to-end models for Document Image Enhancement (DIE) using deep learning models were presented. First, Generative Adversarial Networks (cGAN) for different tasks (document clean-up, binarization, deblurring, and watermark removal) were explored. Next, we further improve the results by recovering the degraded document images into a clean and readable form by integrating a text recognizer into the cGAN model to promote the generated document image to be more readable. Afterward, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion.
The second part of the thesis addresses Handwritten Text Recognition (HTR) in low resource scenarios, i.e. when only few labeled training data is available. We propose novel methods for recognizing ciphers with rare scripts. First, a few-shot object detection based method was proposed. Then, we incorporate a progressive learning strategy that automatically assignspseudo-labels to a set of unlabeled data to reduce the human labor of annotating few pages while maintaining the good performance of the model. Secondly, a data generation technique based on Bayesian Program Learning (BPL) is proposed to overcome the lack of data in such rare scripts. Thirdly, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE). This latter self-supervised model is designed to tackle two tasks, text recognition and document image enhancement. The proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time, it requires substantially fewer data samples to converge.
In the third part of the thesis, we analyze, from the user perspective, the usage of HTR systems in low resource scenarios. This contrasts with the usual research on HTR, which often focuses on technical aspects only and rarely devotes efforts on implementing software tools for scholars in Humanities.
|
|
|
|
Juan Ignacio Toledo. 2019. Information Extraction from Heterogeneous Handwritten Documents. (Ph.D. thesis, Ediciones Graficas Rey.)
Abstract: In this thesis we explore information Extraction from totally or partially handwritten documents. Basically we are dealing with two different application scenarios. The first scenario are modern highly structured documents like forms. In this kind of documents, the semantic information is encoded in different fields with a pre-defined location in the document, therefore, information extraction becomes roughly equivalent to transcription. The second application scenario are loosely structured totally handwritten documents, besides transcribing them, we need to assign a semantic label, from a set of known values to the handwritten words.
In both scenarios, transcription is an important part of the information extraction. For that reason in this thesis we present two methods based on Neural Networks, to transcribe handwritten text.In order to tackle the challenge of loosely structured documents, we have produced a benchmark, consisting of a dataset, a defined set of tasks and a metric, that was presented to the community as an international competition. Also, we propose different models based on Convolutional and Recurrent neural networks that are able to transcribe and assign different semantic labels to each handwritten words, that is, able to perform Information Extraction.
|
|
|
|
George Tom, Minesh Mathew, Sergi Garcia Bordils, Dimosthenis Karatzas and CV Jawahar. 2023. ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. 17th International Conference on Document Analysis and Recognition.577–586. (LNCS.)
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.
|
|
|
|
Ruben Tito, Minesh Mathew, C.V. Jawahar, Ernest Valveny and Dimosthenis Karatzas. 2021. ICDAR 2021 Competition on Document Visual Question Answering. 16th International Conference on Document Analysis and Recognition.635–649.
Abstract: In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5, 000 infographics images and 30, 000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented.
|
|
|
|
Juan Ignacio Toledo, Jordi Cucurull, Jordi Puiggali, Alicia Fornes and Josep Llados. 2015. Document Analysis Techniques for Automatic Electoral Document Processing: A Survey. E-Voting and Identity, Proceedings of 5th international conference, VoteID 2015.139–141. (LNCS.)
Abstract: In this paper, we will discuss the most common challenges in electoral document processing and study the different solutions from the document analysis community that can be applied in each case. We will cover Optical Mark Recognition techniques to detect voter selections in the Australian Ballot, handwritten number recognition for preferential elections and handwriting recognition for write-in areas. We will also propose some particular adjustments that can be made to those general techniques in the specific context of electoral documents.
Keywords: Document image analysis; Computer vision; Paper ballots; Paper based elections; Optical scan; Tally
|
|
|
|
Marçal Rusiñol and Josep Llados. 2014. Boosting the Handwritten Word Spotting Experience by Including the User in the Loop. PR, 47(3), 1063–1072.
Abstract: In this paper, we study the effect of taking the user into account in a query-by-example handwritten word spotting framework. Several off-the-shelf query fusion and relevance feedback strategies have been tested in the handwritten word spotting context. The increase in terms of precision when the user is included in the loop is assessed using two datasets of historical handwritten documents and two baseline word spotting approaches both based on the bag-of-visual-words model. We finally present two alternative ways of presenting the results to the user that might be more attractive and suitable to the user's needs than the classic ranked list.
Keywords: Handwritten word spotting; Query by example; Relevance feedback; Query fusion; Multidimensional scaling
|
|
|
|
Lluis Pere de las Heras, Oriol Ramos Terrades and Josep Llados. 2015. Attributed Graph Grammar for floor plan analysis. 13th International Conference on Document Analysis and Recognition ICDAR2015.726–730.
Abstract: In this paper, we propose the use of an Attributed Graph Grammar as unique framework to model and recognize the structure of floor plans. This grammar represents a building as a hierarchical composition of structurally and semantically related elements, where common representations are learned stochastically from annotated data. Given an input image, the parsing consists on constructing that graph representation that better agrees with the probabilistic model defined by the grammar. The proposed method provides several advantages with respect to the traditional floor plan analysis techniques. It uses an unsupervised statistical approach for detecting walls that adapts to different graphical notations and relaxes strong structural assumptions such are straightness and orthogonality. Moreover, the independence between the knowledge model and the parsing implementation allows the method to learn automatically different building configurations and thus, to cope the existing variability. These advantages are clearly demonstrated by comparing it with the most recent floor plan interpretation techniques on 4 datasets of real floor plans with different notations.
|
|
