Abstract: This thesis presents several contributions to the literature of sketch based image retrieval (SBIR). In SBIR the first challenge we face is how to map two different domains to common space for effective retrieval of images, while tackling the different levels of abstraction people use to express their notion of objects around while sketching. To this extent we first propose a cross-modal learning framework that maps both sketches and text into a joint embedding space invariant to depictive style, while preserving semantics. Then we have also investigated different query types possible to encompass people's dilema in sketching certain world objects. For this we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set.
Finally, we explore the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognises two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended. We also in this dissertation pave the path to the future direction of research in this domain.

Abstract: Though they achieve great success, deep neural networks typically require a huge
amount of labeled data for training. However, collecting labeled data is often laborious and expensive. It would, therefore, be ideal if the knowledge obtained from label-rich datasets could be transferred to unlabeled data. However, deep networks are weak at generalizing to unseen domains, even when the differences are only subtle between the datasets. In real-world situations, a typical factor impairing the model generalization ability is the distribution shift between data from different domains, which is a long-standing problem usually termed as (unsupervised) domain adaptation.
A crucial requirement in the methodology of these domain adaptation methods is that they require access to source domain data during the adaptation process to the target domain. Accessibility to the source data of a trained source model is often impossible in real-world applications, for example, when deploying domain adaptation algorithms on mobile devices where the computational capacity is limited or in situations where data privacy rules limit access to the source domain data. Without access to the source domain data, existing methods suffer from inferior performance. Thus, in this thesis, we investigate domain adaptation without source data (termed as source-free domain adaptation) in multiple different scenarios that focus on image classification tasks.
We first study the source-free domain adaptation problem in a closed-set setting,
where the label space of different domains is identical. Only accessing the pretrained source model, we propose to address source-free domain adaptation from the perspective of unsupervised clustering. We achieve this based on nearest neighborhood clustering. In this way, we can transfer the challenging source-free domain adaptation task to a type of clustering problem. The final optimization objective is an upper bound containing only two simple terms, which can be explained as discriminability and diversity. We show that this allows us to relate several other methods in domain adaptation, unsupervised clustering and contrastive learning via the perspective of discriminability and diversity.

Abstract: Image registration has been for many years the gold standard method to bring two images into correspondence. It has been used extensively in the eld of medical imaging in order to put images of dierent patients into a common overlapping spatial position. However, medical image registration is a slow, iterative optimization process, where many variables and prone to fall into the pit traps local minima.
A coordinate system parameterizing the interior of organs is a powerful tool for a systematic localization of injured tissue. If the same coordinate values are assigned to specic anatomical sites, parameterizations ensure integration of data across different medical image modalities. Harmonic mappings have been used to produce parametric meshes over the surface of anatomical shapes, given their ability to set values at specic locations through boundary conditions. However, most of the existing implementations in medical imaging restrict to either anatomical surfaces, or the depth coordinate with boundary conditions is given at discrete sites of limited geometric diversity.
The medial surface of the shape can be used to provide a continuous basis for the denition of a depth coordinate. However, given that dierent methods for generation of medial surfaces generate dierent manifolds, not all of them are equally suited to be the basis of radial coordinate for a parameterization. It would be desirable that the medial surface will be smooth, and robust to surface shape noise, with low number of spurious branches or surfaces.
In this thesis we present methods for computation of smooth medial manifolds and apply them to the generation of for anatomical volumetric parameterization that extends current harmonic parameterizations to the interior anatomy using information provided by the volume medial surface. This reference system sets a solid base for creating anatomical models of the anatomical shapes, and allows comparing several patients in a common framework of reference.

Abstract: The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting.
Inpainting and Denoising Challenges comprises recent efforts dealing with image and video inpainting tasks. This includes winning solutions to the ChaLearn Looking at People inpainting and denoising challenges: human pose recovery, video de-captioning and fingerprint restoration.
This volume starts with a wide review on image denoising, retracing and comparing various methods from the pioneer signal processing methods, to machine learning approaches with sparse and low-rank models, and recent deep learning architectures with autoencoders and variants. The following chapters present results from the Challenge, including three competition tasks at WCCI and ECML 2018. The top best approaches submitted by participants are described, showing interesting contributions and innovating methods. The last two chapters propose novel contributions and highlight new applications that benefit from image/video inpainting.

Abstract: Many real problems require multi-class decisions. In the Pattern Recognition field,
many techniques have been proposed to deal with the binary problem. However,
the extension of many 2-class classifiers to the multi-class case is a hard task. In
this sense, Error-Correcting Output Codes (ECOC) demonstrated to be a powerful
tool to combine any number of binary classifiers to model multi-class problems. But
there are still many open issues about the capabilities of the ECOC framework. In
this thesis, the two main stages of an ECOC design are analyzed: the coding and
the decoding steps. We present different problem-dependent designs. These designs
take advantage of the knowledge of the problem domain to minimize the number
of classifiers, obtaining a high classification performance. On the other hand, we
analyze the ECOC codification in order to define new decoding rules that take full
benefit from the information provided at the coding step. Moreover, as a successful
classification requires a rich feature set, new feature detection/extraction techniques
are presented and evaluated on the new ECOC designs. The evaluation of the new
methodology is performed on different real and synthetic data sets: UCI Machine
Learning Repository, handwriting symbols, traffic signs from a Mobile Mapping System, Intravascular Ultrasound images, Caltech Repository data set or Chaga’s disease
data set. The results of this thesis show that significant performance improvements
are obtained on both traditional coding and decoding ECOC designs when the new
coding and decoding rules are taken into account.

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.