Abstract: The representation (or feature) learning has been an emerging concept in the last years, since it collects a set of techniques that are present in any theoretical or practical methodology referring to artificial intelligence. In computer vision, a very common representation has adopted the form of the well-known Bag of Visual Words. This representation appears implicitly in most approaches where images are described, and is also present in a huge number of areas and domains: image content retrieval, pedestrian detection, human-computer interaction, surveillance, e-health, and social computing, amongst others. The early stages of this dissertation provide an approach for learning visual representations inside evolutionary algorithms, which consists of evolving weighting schemes to improve the BoVW representations for the task of recognizing categories of videos and images. Thus, we demonstrate the applicability of the most common weighting schemes, which are often used in text mining but are less frequently found in computer vision tasks. Beyond learning these visual representations, we provide an approach based on fusion strategies for learning spatiotemporal representations, from multimodal data obtained by depth sensors. Besides, we specially aim at the evolutionary and dynamic modelling, where the temporal factor is present in the nature of the data, such as video sequences of gestures and actions. Indeed, we explore the effects of probabilistic modelling for those approaches based on dynamic programming, so as to handle the temporal deformation and variance amongst video sequences of different categories. Finally, we integrate dynamic programming and generative models into an evolutionary computation framework, with the aim of learning Bags of SubGestures (BoSG) representations and hence to improve the generalization capability of standard gesture recognition approaches. The results obtained in the experimentation demonstrate, first, that evolutionary algorithms are useful for improving the representation of BoVW approaches in several datasets for recognizing categories in still images and video sequences. On the other hand, our experimentation reveals that both, the use of dynamic programming and generative models to align video sequences, and the representations obtained from applying fusion strategies in multimodal data, entail an enhancement on the performance when recognizing some gesture categories. Furthermore, the combination of evolutionary algorithms with models based on dynamic programming and generative approaches results, when aiming at the classification of video categories on large video datasets, in a considerable improvement over standard gesture and action recognition approaches. Finally, we demonstrate the applications of these representations in several domains for human analysis: classification of images where humans may be present, action and gesture recognition for general applications, and in particular for conversational settings within the field of restorative justice

Abstract: Desde la implantación del Espacio Europeo de Educación Superior (EEES) en los diferentes grados, se ha puesto de manifiesto la necesidad de utilizar diversos mecanismos que permitan tratar la diversidad en el aula, evaluando automáticamente y proporcionando una retroalimentación rápida tanto al alumnado como al profesorado sobre la evolución de los alumnos en una asignatura. En este artículo se presenta la evaluación de la exactitud en las predicciones de GRADEFORESEER, un recurso docente para la predicción de notas basado en técnicas de aprendizaje automático que permite evaluar la evolución del alumnado y estimar su nota final al terminar el curso. Este recurso se ha complementado con una interfaz de usuario para el profesorado que puede ser usada en diferentes plataformas software (sistemas operativos) y en cualquier asignatura de un grado en la que se utilice evaluación continuada. Además de la descripción del recurso, este artículo presenta los resultados obtenidos al aplicar el sistema de predicción en cuatro asignaturas de disciplinas distintas: Programación I (PI), Diseño de Software (DSW) del grado de Ingeniería Informática, Tecnologías de la Información y la Comunicación (TIC) del grado de Lingüística y la asignatura Fundamentos de Tecnología (FDT) del grado de Información y Documentación, todas ellas impartidas en la Universidad de Barcelona.
La capacidad predictiva se ha evaluado de forma binaria (aprueba o no) y según un criterio de rango (suspenso, aprobado, notable o sobresaliente), obteniendo mejores predicciones en los resultados evaluados de forma binaria.

Abstract: Nonverbal communication is an intrinsic part in daily face-to-face meetings. A frequently observed behavior during social interactions is mirroring, in which one person tends to mimic the attitude of the counterpart. This paper shows that a computer vision system could be used to predict the perception of competence in dyadic interactions through the automatic detection of mirroring
events. To prove our hypothesis, we developed: (1) A social assistant for mirroring detection, using a wearable device which includes a video camera and (2) an automatic classifier for the perception of competence, using the number of nodding gestures and mirroring events as predictors. For our study, we used a mixed-method approach in an experimental design where 48 participants acting as customers interacted with a confederated psychologist. We found that the number of nods or mirroring events has a significant influence on the perception of competence. Our results suggest that: (1) Customer mirroring is a better predictor than psychologist mirroring; (2) the number of psychologist’s nods is a better predictor than the number of customer’s nods; (3) except for the psychologist mirroring, the computer vision algorithm we used worked about equally well whether it was acquiring images from wearable smartglasses or fixed cameras.

Abstract: The interpretation and analysis of wireless capsule endoscopy (WCE) recordings is a complex task which requires sophisticated computer aided decision (CAD) systems to help physicians with video screening and, finally, with the diagnosis. Most CAD systems used in capsule endoscopy share a common system design, but use very different image and video representations. As a result, each time a new clinical application of WCE appears, a new CAD system has to be designed from the scratch. This makes the design of new CAD systems very time consuming. Therefore, in this paper we introduce a system for small intestine motility characterization, based on Deep Convolutional Neural Networks, which circumvents the laborious step of designing specific features for individual motility events. Experimental results show the superiority of the learned features over alternative classifiers constructed using state-of-the-art handcrafted features. In particular, it reaches a mean classification accuracy of 96% for six intestinal motility events, outperforming the other classifiers by a large margin (a 14% relative performance increase).

Abstract: This paper proposes a technique for RGB-D scene segmentation using Multi-class
Multi-scale Stacked Sequential Learning (MMSSL) paradigm. Following recent trends in state-of-the-art, a base classifier uses an initial SLIC segmentation to obtain superpixels which provide a diminution of data while retaining object boundaries. A series of color and depth features are extracted from the superpixels, and are used in a Conditional Random Field (CRF) to predict superpixel labels. Furthermore, a Random Forest (RF) classifier using random offset features is also used as an input to the CRF, acting as an initial prediction. As a stacked classifier, another Random Forest is used acting on a spatial multi-scale decomposition of the CRF confidence map to correct the erroneous labels assigned by the previous classifier. The model is tested on the popular NYU-v2 dataset.
The approach shows that simple multi-modal features with the power of the MMSSL
paradigm can achieve better performance than state of the art results on the same dataset.

Abstract: Reliable facial recognition systems are of crucial importance in various applications from entertainment to security. Thanks to the deep-learning concepts introduced in the field, a significant improvement in the performance of the unimodal facial recognition systems has been observed in the recent years. At the same time a multimodal facial recognition is a promising approach. This study combines the latest successes in both directions by applying deep learning convolutional neural networks (CNN) to the multimodal RGB, depth, and thermal (RGB-D-T) based facial recognition problem outperforming previously published results. Furthermore, a late fusion of the CNN-based recognition block with various hand-crafted features (local binary patterns, histograms of oriented gradients, Haar-like rectangular features, histograms of Gabor ordinal measures) is introduced, demonstrating even better recognition performance on a benchmark RGB-D-T database. The obtained results in this study show that the classical engineered features and CNN-based features can complement each other for recognition purposes.

Abstract: Latest advances in digitization techniques have fostered the interest in creating digital copies of collections of documents. Digitized documents permit an easy maintenance, loss-less storage, and efficient ways for transmission and to perform information retrieval processes. This situation has opened a new market niche to develop systems able to automatically extract and analyze information contained in these collections, specially in the ambit of the business activity.
Due to the great variety of types of documents this is not a trivial task. For instance, the automatic extraction of numerical data from invoices differs substantially from a task of text recognition in historical documents. However, in order to extract the information of interest, is always necessary to identify the area of the document where it is located. In the area of Document Analysis we refer to this process as layout analysis, which aims at identifying and categorizing the different entities that compose the document, such as text regions, pictures, text lines, or tables, among others. To perform this task it is usually necessary to incorporate a prior knowledge about the task into the analysis process, which can be modeled by defining a set of contextual relations between the different entities of the document. The use of context has proven to be useful to reinforce the recognition process and improve the results on many computer vision tasks. It presents two fundamental questions: What kind of contextual information is appropriate for a given task, and how to incorporate this information into the models.
In this thesis we study several ways to incorporate contextual information to the task of document layout analysis, and to the particular case of handwritten text line segmentation. We focus on the study of Probabilistic Graphical Models and other mechanisms for this purpose, and propose several solutions to these problems. First, we present a method for layout analysis based on Conditional Random Fields. With this model we encode local contextual relations between variables, such as pair-wise constraints. Besides, we encode a set of structural relations between different classes of regions at feature level. Second, we present a method based on 2D-Probabilistic Context-free Grammars to encode structural and hierarchical relations. We perform a comparative study between Probabilistic Graphical Models and this syntactic approach. Third, we propose a method for structured documents based on Bayesian Networks to represent the document structure, and an algorithm based in the Expectation-Maximization to find the best configuration of the page. We perform a thorough evaluation of the proposed methods on two particular collections of documents: a historical collection composed of ancient structured documents, and a collection of contemporary documents. In addition, we present a general method for the task of handwritten text line segmentation. We define a probabilistic framework where we combine the EM algorithm with variational approaches for computing inference and parameter learning on a Markov Random Field. We evaluate our method on several collections of documents, including a general dataset of annotated administrative documents. Results demonstrate the applicability of our method to real problems, and the contribution of the use of contextual information to this kind of problems.

Abstract: Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved.