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: In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor which is subsequently encoded into a small number of bits. We note that most encoding techniques include an unsupervised dimensionality reduction step. Our goal in this work is to learn a better subspace in a supervised manner. We especially raise the following question: “can category-level labels be used to learn such a subspace?” To answer this question, we experiment with four learning techniques: the first one is based on a metric learning framework, the second one on attribute representations, the third one on Canonical Correlation Analysis (CCA) and the fourth one on Joint Subspace and Classifier Learning (JSCL). While the first three approaches have been applied in the past to the image retrieval problem, we believe we are the first to show the usefulness of JSCL in this context. In our experiments, we use ImageNet as a source of category-level labels and report retrieval results on two standard dataseis: INRIA Holidays and the University of Kentucky benchmark. Our experimental study shows that metric learning and attributes do not lead to any significant improvement in retrieval accuracy, as opposed to CCA and JSCL. As an example, we report on Holidays an increase in accuracy from 39.3% to 48.6% with 32-dimensional representations. Overall JSCL is shown to yield the best results.

Abstract: Semantic image retrieval from large amounts of egocentric visual data requires to leverage powerful techniques for filling in the semantic gap. This paper introduces LEMoRe, a Lifelog Engine for Moments Retrieval, developed in the context of the Lifelog Semantic Access Task (LSAT) of the the NTCIR-12 challenge and discusses its performance variation on different trials. LEMoRe integrates classical image descriptors with high-level semantic concepts extracted by Convolutional Neural Networks (CNN), powered by a graphic user interface that uses natural language processing. Although this is just a first attempt towards interactive image retrieval from large egocentric datasets and there is a large room for improvement of the system components and the user interface, the structure of the system itself and the way the single components cooperate are very promising.

Abstract: Due to its complex geometry, the basal ring is often omitted when putting different heart geometries into correspondence. In this paper, we present the first results on a new mapping of the left ventricle basal rings onto a normalized coordinate system using a fold-over free approach to the solution to the Laplacian. To guarantee correspondences between different basal rings, we imposed some internal constrained positions at anatomical landmarks in the normalized coordinate system. To prevent internal fold-overs, constraints are handled by cutting the volume into regions defined by anatomical features and mapping each piece of the volume separately. Initial results presented in this paper indicate that our method is able to handle internal constrains without introducing fold-overs and thus guarantees one-to-one mappings between different basal ring geometries.

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: Writing is one of the most important forms of communication and for centuries, handwriting had been the most reliable way to preserve knowledge. However, despite the recent development of printing houses and electronic devices, handwriting is still broadly used for taking notes, doing annotations, or sketching ideas.
Transferring the ability of understanding handwritten text or recognizing handwritten shapes to computers has been the goal of many researches due to its huge importance for many different fields. However, designing good representations to deal with handwritten shapes, e.g. symbols or words, is a very challenging problem due to the large variability of these kinds of shapes. One of the consequences of working with handwritten shapes is that we need representations to be robust, i.e., able to adapt to large intra-class variability. We need representations to be discriminative, i.e., able to learn what are the differences between classes. And, we need representations to be efficient, i.e., able to be rapidly computed and compared. Unfortunately, current techniques of handwritten shape representation for matching and recognition do not fulfill some or all of these requirements.
Through this thesis we focus on the problem of learning to represent handwritten shapes aimed at retrieval and recognition tasks. Concretely, on the first part of the thesis, we focus on the general problem of representing any kind of handwritten shape. We first present a novel shape descriptor based on a deformable grid that deals with large deformations by adapting to the shape and where the cells of the grid can be used to extract different features. Then, we propose to use this descriptor to learn statistical models, based on the Active Appearance Model, that jointly learns the variability in structure and texture of a given class. Then, on the second part, we focus on a concrete application, the problem of representing handwritten words, for the tasks of word spotting, where the goal is to find all instances of a query word in a dataset of images, and recognition. First, we address the segmentation-free problem and propose an unsupervised, sliding-window-based approach that achieves state-of- the-art results in two public datasets. Second, we address the more challenging multi-writer problem, where the variability in words exponentially increases. We describe an approach in which both word images and text strings are embedded in a common vectorial subspace, and where those that represent the same word are close together. This is achieved by a combination of label embedding and attributes learning, and a common subspace regression. This leads to a low-dimensional, unified representation of word images and strings, resulting in a method that allows one to perform either image and text searches, as well as image transcription, in a unified framework. We evaluate our methods on different public datasets of both handwritten documents and natural images showing results comparable or better than the state-of-the-art on spotting and recognition tasks.

Abstract: Action recognition is a very challenging and important problem in computer vi­sion. Researchers working on this field aspire to provide computers with the abil­ ity to visually perceive human actions – that is, to observe, interpret, and under­ stand human-related events that occur in the physical environment merely from visual data. The applications of this technology are numerous: human-machine interaction, e-health, monitoring/surveillance, and content-based video retrieval, among others. Hand-crafted methods dominated the field until the apparition of the first successful deep learning-based action recognition works. Although ear­ lier deep-based methods underperformed with respect to hand-crafted approaches, these slowly but steadily improved to become state-of-the-art, eventually achieving better results than hand-crafted ones. Still, hand-crafted approaches can be advan­ tageous in certain scenarios, specially when not enough data is available to train very large deep models or simply to be combined with deep-based methods to fur­ ther boost the performance. Hence, showing how hand-crafted features can provide extra knowledge the deep networks are notable to easily learn about human actions.
This Thesis concurs in time with this change of paradigm and, hence, reflects it into two distinguished parts. In the first part, we focus on improving current suc­ cessful hand-crafted approaches for action recognition and we do so from three dif­ ferent perspectives. Using the dense trajectories framework as a backbone: first, we explore the use of multi-modal and multi-view input
data to enrich the trajectory de­ scriptors. Second, we focus on the classification part of action recognition pipelines and propose an ensemble learning approach, where each classifier leams from a dif­ferent set of local spatiotemporal features to then combine their outputs following an strategy based on the Dempster-Shaffer Theory. And third, we propose a novel hand-crafted feature extraction method that constructs a rnid-level feature descrip­ tion to better modellong-term spatiotemporal dynarnics within action videos. Moving to the second part of the Thesis, we start with a comprehensive study of the current deep-learning based action recognition methods. We review both fun­ damental and cutting edge methodologies reported during the last few years and introduce a taxonomy of deep-leaming methods dedicated to action recognition. In particular, we analyze and discuss how these handle
the temporal dimension of data. Last but not least, we propose a residual recurrent network for action recogni­ tion that naturally integrates all our previous findings in a powerful and prornising framework.

Abstract: In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder. We consider retrieval frameworks in which the user expects a retrieval list ranked according to a defined relevance score. In the context of a word spotting problem, the relevance score has been set according to the string edit distance from the query string. We experimentally demonstrate the competitive performance of the proposed model on query-by-string word spotting for both, handwritten and real scene word images. We also provide the results for query-by-example word spotting, although it is not the main focus of this work.