Abstract: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.

Abstract: Anisotropic differential operators are widely used in image enhancement processes. Recently, their property of smoothly extending functions to the whole image domain has begun to be exploited. Strong ellipticity of differential operators is a requirement that ensures existence of a unique solution. This condition is too restrictive for operators designed to extend image level sets: their own functionality implies that they should restrict to some vector field. The diffusion tensor that defines the diffusion operator links anisotropic processes with Riemmanian manifolds. In this context, degeneracy implies restricting diffusion to the varieties generated by the vector fields of positive eigenvalues, provided that an integrability condition is satisfied. We will use that any smooth vector field fulfills this integrability requirement to design line connection algorithms for contour completion. As application we present a segmenting strategy that assures convergent snakes whatever the geometry of the object to be modelled is.

Abstract: In this article, a method to extract the rooms of an architectural floor plan image is described. We first present a line detection algorithm to extract long lines in the image. Those lines are analyzed to identify the existing walls. From this point, room extraction can be seen as a classical segmentation task for which each region corresponds to a room. The chosen resolution strategy consists in recursively decomposing the image until getting nearly convex regions. The notion of convexity is difficult to quantify, and the selection of separation lines can also be rough. Thus, we take advantage of knowledge associated to architectural floor plans in order to obtain mainly rectangular rooms. Preliminary tests on a set of real documents show promising results.

Abstract: In the recent years commercial eye-tracking hardware has become more common, with the introduction of new models from several brands that have better performance and easier setup procedures. A cause and at the same time a result of this phenomenon is the popularity of eye-tracking research directed at marketing, accessibility and usability, among others.
One problem with these hardware components is scalability, because both the price and the necessary expertise to operate them makes it practically impossible in the large scale. In this work, we analyze the feasibility of a software eye-tracking system based on a single, ordinary webcam. Our aim is to discover the limits of such a system and to see whether it provides acceptable performances.
The significance of this setup is that it is the most common setup found in consumer environments, off-the-shelf electronic devices such as laptops, mobile phones and tablet computers. As no special equipment such as infrared lights, mirrors or zoom lenses are used; setting up and calibrating the system is easier compared to other approaches using these components.
Our work is based on the open source application Opengazer, which provides a good starting point for our contributions. We propose several improvements in order to push the system's performance further and make it feasible as a robust, real-time device. Then we carry out an elaborate experiment involving 18 human subjects and 4 different system setups. Finally, we give an analysis of the results and discuss the effects of setup changes, subject differences and modifications in the software.

Abstract: Photorealistic virtual environments are crucial for developing and testing automated driving systems in a safe way during trials. As commercially available simulators are expensive and bulky, this paper presents a low-cost, extendable, and easy-to-use (LEE) virtual environment with the aim to highlight its utility for level 3 driving automation. In particular, an experiment is performed using the presented simulator to explore the influence of different variables regarding control transfer of the car after the system was driving autonomously in a highway scenario. The results show that the speed of the car at the time when the system needs to transfer the control to the human driver is critical.

Abstract: With the ubiquity of facial authentication systems and the prevalence of security cameras around the world, the impact that facial presentation attack techniques may have is huge. However, research progress in this field has been slowed by a number of factors, including the lack of appropriate and realistic datasets, ethical and privacy issues that prevent the recording and distribution of facial images, the little attention that the community has given to potential ethnic biases among others. This chapter provides an overview of contributions derived from the organization of academic challenges in the context of face anti-spoofing detection. Specifically, we discuss the limitations of benchmarks and summarize our efforts in trying to boost research by the community via the participation in academic challenges