Abstract: Pattern recognition is the task that aims at distinguishing objects among different classes. When such a task wants to be solved in an automatic way a crucial step is how to formally represent such patterns to the computer. Based on the different representational formalisms, we may distinguish between statistical and structural pattern recognition. The former describes objects as a set of measurements arranged in the form of what is called a feature vector. The latter assumes that relations between parts of the underlying objects need to be explicitly represented and thus it uses relational structures such as graphs for encoding their inherent information. Vector spaces are a very flexible mathematical structure that has allowed to come up with several efficient ways for the analysis of patterns under the form of feature vectors. Nevertheless, such a representation cannot explicitly cope with binary relations between parts of the objects and it is restricted to measure the exact same number of features for each pattern under study regardless of their complexity. Graph-based representations present the contrary situation. They can easily adapt to the inherent complexity of the patterns but introduce a problem of high computational complexity, hindering the design of efficient tools to process and analyse patterns.
Solving this paradox is the main goal of this thesis. The ideal situation for solving pattern recognition problems would be to represent the patterns using relational structures such as graphs, and to be able to use the wealthy repository of data processing tools from the statistical pattern recognition domain. An elegant solution to this problem is to transform the graph domain into a vector domain where any processing algorithm can be applied. In other words, by mapping each graph to a point in a vector space we automatically get access to the rich set of algorithms from the statistical domain to be applied in the graph domain. Such methodology is called graph embedding.
In this thesis we propose to associate feature vectors to graphs in a simple and very efficient way by just putting attention on the labelling information that graphs store. In particular, we count frequencies of node labels and of edges between labels. Although their locality, these features are able to robustly represent structurally global properties of graphs, when considered together in the form of a vector. We initially deal with the case of discrete attributed graphs, where features are easy to compute. The continuous case is tackled as a natural generalization of the discrete one, where rather than counting node and edge labelling instances, we count statistics of some representatives of them. We encounter how the proposed vectorial representations of graphs suffer from high dimensionality and correlation among components and we face these problems by feature selection algorithms. We also explore how the diversity of different embedding representations can be exploited in order to boost the performance of base classifiers in a multiple classifier systems framework. An extensive experimental evaluation finally shows how the methodology we propose can be efficiently computed and compete with other graph matching and embedding methodologies.

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: Machine learning experimentation under controlled scenarios and standard datasets is necessary to compare algorithms performance by evaluating all of them in the same setup. However, experimentation on how those algorithms perform on unconstrained data and applied tasks to solve real world problems is also a must to ascertain how that research can contribute to our society.
In this dissertation we experiment with the latest computer vision and natural language processing algorithms applying them to multimodal scene interpretation. Particularly, we research on how image and text understanding can be jointly exploited to address real world problems, focusing on learning from Social Media data.
We address several tasks that involve image and textual information, discuss their characteristics and offer our experimentation conclusions. First, we work on detection of scene text in images. Then, we work with Social Media posts, exploiting the captions associated to images as supervision to learn visual features, which we apply to multimodal semantic image retrieval. Subsequently, we work with geolocated Social Media images with associated tags, experimenting on how to use the tags as supervision, on location sensitive image retrieval and on exploiting location information for image tagging. Finally, we work on a specific classification problem of Social Media publications consisting on an image and a text: Multimodal hate speech classification.

Abstract: Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while
requiring significantly less data to converge.

Abstract: Text understanding in scene images has gained plenty of attention in the computer vision community and it is an important task in many applications as text carries semantically rich information about scene content and context. For instance, reading text in a scene can be applied to autonomous driving, scene understanding or assisting visually impaired people. The general aim of scene text understanding is to localize and recognize text in scene images. Text regions are first localized in the original image by a trained detector model and afterwards fed into a recognition module. The tasks of localization and recognition are highly correlated since an inaccurate localization can affect the recognition task.
The main purpose of this thesis is to devise efficient methods for scene text understanding. We investigate how the latest results on deep learning can advance text understanding pipelines. Recently, Fully Convolutional Networks (FCNs) and derived methods have achieved a significant performance on semantic segmentation and pixel level classification tasks. Therefore, we took benefit of the strengths of FCN approaches in order to detect text in natural scenes. In this thesis we have focused on two challenging tasks of scene text understanding which are Text Detection and Word Spotting. For the task of text detection, we have proposed an efficient text proposal technique in scene images. We have considered the Text Proposals method as the baseline which is an approach to reduce the search space of possible text regions in an image. In order to improve the Text Proposals method we combined it with Fully Convolutional Networks to efficiently reduce the number of proposals while maintaining the same level of accuracy and thus gaining a significant speed up. Our experiments demonstrate that this text proposal approach yields significantly higher recall rates than the line based text localization techniques, while also producing better-quality localization. We have also applied this technique on compressed images such as videos from wearable egocentric cameras. For the task of word spotting, we have introduced a novel mid-level word representation method. We have proposed a technique to create and exploit an intermediate representation of images based on text attributes which roughly correspond to character probability maps. Our representation extends the concept of Pyramidal Histogram Of Characters (PHOC) by exploiting Fully Convolutional Networks to derive a pixel-wise mapping of the character distribution within candidate word regions. We call this representation the Soft-PHOC. Furthermore, we show how to use Soft-PHOC descriptors for word spotting tasks through an efficient text line proposal algorithm. To evaluate the detected text, we propose a novel line based evaluation along with the classic bounding box based approach. We test our method on incidental scene text images which comprises real-life scenarios such as urban scenes. The importance of incidental scene text images is due to the complexity of backgrounds, perspective, variety of script and language, short text and little linguistic context. All of these factors together makes the incidental scene text images challenging.