Abstract: Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.

Abstract: We describe a general framework for the recognition of distorted images of lineal shapes, which relies on three items: a model to represent lineal shapes and their deformations, a model for the generation of distorted binary images and the combination of both models in a common probabilistic framework, where the generation of deformations is related to an internal energy, and the generation of binary images to an external energy. Then, recognition consists in the minimization of a global energy function, performed by using the EM algorithm. This general framework has been applied to the recognition of hand-drawn lineal symbols in graphic documents.

Abstract: The automatic processing of handwritten historical documents is considered a hard problem in pattern recognition. In addition to the challenges given by modern handwritten data, a lack of training data as well as effects caused by the degradation of documents can be observed. In this scenario, keyword spotting arises to be a viable solution to make documents amenable for searching and browsing. For this task we propose the adaptation of shape descriptors used in symbol recognition. By treating each word image as a shape, it can be represented using the Blurred Shape Model and the De-formable Blurred Shape Model. Experiments on the George Washington database demonstrate that this approach is able to outperform the commonly used Dynamic Time Warping approach.