Abstract: For millennia, the study of the couple brain-mind has fascinated the humanity in order to understand the complex nature of cognitive states. A cognitive state is the state of the mind at a specific time and involves cognition activities to acquire and process information for making a decision, solving a problem, or achieving a goal.
While normal cognitive states assist in the successful accomplishment of tasks; on the contrary, abnormal states of the mind can lead to task failures due to a reduced cognition capability. In this thesis, we focus on the assessment of cognitive states by means of the analysis of ElectroEncephaloGrams (EEG) signals using deep learning methods. EEG records the electrical activity of the brain using a set of electrodes placed on the scalp that output a set of spatiotemporal signals that are expected to be correlated to a specific mental process.
From the point of view of artificial intelligence, any method for the assessment of cognitive states using EEG signals as input should face several challenges. On the one hand, one should determine which is the most suitable approach for the optimal combination of the multiple signals recorded by EEG electrodes. On the other hand, one should have a protocol for the collection of good quality unambiguous annotated data, and an experimental design for the assessment of the generalization and transfer of models. In order to tackle them, first, we propose several convolutional neural architectures to perform data fusion of the signals recorded by EEG electrodes, at raw signal and feature levels. Four channel fusion methods, easy to incorporate into any neural network architecture, are proposed and assessed. Second, we present a method to create an unambiguous dataset for the prediction of cognitive mental workload using serious games and an Airbus-320 flight simulator. Third, we present a validation protocol that takes into account the levels of generalization of models based on the source and amount of test data.
Finally, the approaches for the assessment of cognitive states are applied to two use cases of high social impact: the assessment of mental workload for personalized support systems in the cockpit and the detection of epileptic seizures. The results obtained from the first use case show the feasibility of task transfer of models trained to detect workload in serious games to real flight scenarios. The results from the second use case show the generalization capability of our EEG channel fusion methods at k-fold cross-validation, patient-specific, and population levels.

Abstract: Guided image processing techniques are widely used for extracting information from a guiding image to aid in the processing of the guided one. These images may be sourced from different modalities, such as 2D and 3D, or different spectral bands, like visible and infrared. In the case of guided cross-spectral super-resolution, features from the two modal images are extracted and efficiently merged to migrate guidance information from one image, usually high-resolution (HR), toward the guided one, usually low-resolution (LR). Different approaches have been recently proposed focusing on the development of architectures for feature extraction and merging in the cross-spectral domains, but none of them care about the different nature of the given images. This paper focuses on the specific problem of guided thermal image super-resolution, where an LR thermal image is enhanced by an HR visible spectrum image. To improve existing guided super-resolution techniques, a novel scheme is proposed that maps the original guiding information to a thermal image-like representation that is similar to the output. Experimental results evaluating five different approaches demonstrate that the best results are achieved when the guiding and guided images share the same domain.

Abstract: Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information given, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. The same Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to the specific context allowing us to explore the limits of the model to adjust captions to different contextual information. Dealing with out-of-dictionary words and Named Entities is a challenging task in this domain. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task results to significantly improved models. Furthermore, we verify that a model pre-trained in Wikipedia generalizes well to News Captioning datasets. We further define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model.

Abstract: In autonomous driving, artificial intelligence (AI) processes the traffic environment to drive the vehicle to a desired destination. Currently, there are different paradigms that address the development of AI-enabled drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception, maneuver planning, and control. On the other hand, we find end-to-end driving approaches that attempt to learn the direct mapping of raw data from input sensors to vehicle control signals. The latter are relatively less studied but are gaining popularity as they are less demanding in terms of data labeling. Therefore, in this thesis, our goal is to investigate end-to-end autonomous driving.
We propose to evaluate three approaches to tackle the challenge of end-to-end
autonomous driving. First, we focus on the input, considering adding depth information as complementary to RGB data, in order to mimic the human being’s
ability to estimate the distance to obstacles. Notice that, in the real world, these depth maps can be obtained either from a LiDAR sensor, or a trained monocular
depth estimation module, where human labeling is not needed. Then, based on
the intuition that the latent space of end-to-end driving models encodes relevant
information for driving, we use it as prior knowledge for training an affordancebased driving model. In this case, the trained affordance-based model can achieve good performance while requiring less human-labeled data, and it can provide interpretability regarding driving actions. Finally, we present a new pure vision-based end-to-end driving model termed CIL++, which is trained by imitation learning.
CIL++ leverages modern best practices, such as a large horizontal field of view and
a self-attention mechanism, which are contributing to the agent’s understanding of
the driving scene and bringing a better imitation of human drivers. Using training
data without any human labeling, our model yields almost expert performance in
the CARLA NoCrash benchmark and could rival SOTA models that require large amounts of human-labeled data.

Abstract: In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model.

Abstract: In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

Abstract: In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, recent studies have highlighted the strengths of self-supervised continual representation learning. The improved transferability of representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning.

Abstract: In this paper, we present a novel hand –based Video Question Answering framework, entitled Multi-View Video Question Answering (MV-VQA), employing the Single Shot Detector (SSD), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT), and Co-Attention mechanism with RGB videos as the inputs. Our model includes three main blocks: vision, language, and attention. In the vision block, we employ a novel representation to obtain some efficient multiview features from the hand object using the combination of five 3DCNNs and one LSTM network. To obtain the question embedding, we use the BERT model in language block. Finally, we employ a co-attention mechanism on vision and language features to recognize the final answer. For the first time, we propose such a hand-based Video-QA framework including the multi-view hand skeleton features combined with the question embedding and co-attention mechanism. Our framework is capable of processing the arbitrary numbers of questions in the dataset annotations. There are different application domains for this framework. Here, as an application domain, we applied our framework to dynamic hand gesture recognition for the first time. Since the main object in dynamic hand gesture recognition is the human hand, we performed a step-by-step analysis of the hand detection and multi-view hand skeleton impact on the model performance. Evaluation results on five datasets, including two datasets in VideoQA, two datasets in dynamic hand gesture, and one dataset in hand action recognition show that MV-VQA outperforms state-of-the-art alternatives.