Abstract: Handwritten documents are not only preserved in historical archives but also widely used in administrative documents such as cheques and claims. With the rise of the deep learning era, many state-of-the-art approaches have achieved good performance on specific datasets for Handwritten Text Recognition (HTR). However, it is still challenging to solve real use cases because of the varied handwriting styles across different writers and the limited labeled data. Thus, both explorin a more robust handwriting recognition architectures and proposing methods to diminish the gap between the source and target data in an unsupervised way are
demanded.
In this thesis, firstly, we explore novel architectures for HTR, from Sequence-to-Sequence (Seq2Seq) method with attention mechanism to non-recurrent Transformer-based method. Secondly, we focus on diminishing the performance gap between source and target data in an unsupervised way. Finally, we propose a group of generative methods for handwritten text images, which could be utilized to increase the training set to obtain a more robust recognizer. In addition, by simply modifying the generative method and joining it with a recognizer, we end up with an effective disentanglement method to distill textual content from handwriting styles so as to achieve a generalized recognition performance.
We outperform state-of-the-art HTR performances in the experimental results among different scientific and industrial datasets, which prove the effectiveness of the proposed methods. To the best of our knowledge, the non-recurrent recognizer and the disentanglement method are the first contributions in the handwriting recognition field. Furthermore, we have outlined the potential research lines, which would be interesting to explore in the future.

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 PhD we have approached the human color vision from two different points of view: psychophysics and computational modeling. First, we have evaluated 15 different tone-mapping operators (TMOs). We have conducted two experiments that
consider two different criteria: the first one evaluates the local relationships among intensity levels and the second one evaluates the global appearance of the tonemapped imagesw.r.t. the physical one (presented side by side). We conclude that the rankings depend on the criterion and they are not correlated. Considering both criteria, the best TMOs are KimKautz (Kim and Kautz, 2008) and Krawczyk (Krawczyk, Myszkowski, and Seidel, 2005). Another conclusion is that a more standardized evaluation criteria is needed to do a fair comparison among TMOs.
Secondly, we have conducted several psychophysical experiments to study the
color induction. We have studied two different properties of the visual stimuli: temporal frequency and luminance spatial distribution. To study the temporal frequency we defined equiluminant stimuli composed by both uniform and striped surrounds and we flashed them varying the flash duration. For uniform surrounds, the results show that color induction depends on both the flash duration and inducer’s chromaticity. As expected, in all chromatic conditions color contrast was induced. In contrast, for striped surrounds, we expected to induce color assimilation, but we observed color contrast or no induction. Since similar but not equiluminant striped stimuli induce color assimilation, we concluded that luminance differences could be a key factor to induce color assimilation. Thus, in a subsequent study, we have studied the luminance differences’ effect on color assimilation. We varied the luminance difference between the target region and its inducers and we observed that color assimilation depends on both this difference and the inducer’s chromaticity. For red-green condition (where the first inducer is red and the second one is green), color assimilation occurs in almost all luminance conditions.
Instead, for green-red condition, color assimilation never occurs. Purple-lime
and lime-purple chromatic conditions show that luminance difference is a key factor to induce color assimilation. When the target is darker than its surround, color assimilation is stronger in purple-lime, while when the target is brighter, color assimilation is stronger in lime-purple (’mirroring’ effect). Moreover, we evaluated whether color assimilation is due to luminance or brightness differences. Similarly to equiluminance condition, when the stimuli are equibrightness no color assimilation is induced. Our results support the hypothesis that mutual-inhibition plays a major role in color perception, or at least in color induction.
Finally, we have defined a new firing rate model of color processing in the V1
parvocellular pathway. We have modeled two different layers of this cortical area: layers 4Cb and 2/3. Our model is a recurrent dynamic computational model that considers both excitatory and inhibitory cells and their lateral connections. Moreover, it considers the existent laminar differences and the cells’ variety. Thus, we have modeled both single- and double-opponent simple cells and complex cells, which are a pool of double-opponent simple cells. A set of sinusoidal drifting gratings have been used to test the architecture. In these gratings we have varied several spatial properties such as temporal and spatial frequencies, grating’s area and orientation. To reproduce the electrophysiological observations, the architecture has to consider the existence of non-oriented double-opponent cells in layer 4Cb and the lack of lateral connections between single-opponent cells. Moreover, we have tested our lateral connections simulating the center-surround modulation and we have reproduced physiological measurements where for high contrast stimulus, the
result of the lateral connections is inhibitory, while it is facilitatory for low contrast stimulus.

Abstract: Anticipating the intentions of vulnerable road users (VRUs) such as pedestrians
and cyclists can be critical for performing safe and comfortable driving maneuvers. This is the case for human driving and, therefore, should be taken into account by systems providing any level of driving assistance, i.e. from advanced driver assistant systems (ADAS) to fully autonomous vehicles (AVs). In this PhD work, we show how the latest advances on monocular vision-based human pose estimation, i.e. those relying on deep Convolutional Neural Networks (CNNs), enable to recognize the intentions of such VRUs. In the case of cyclists, we assume that they follow the established traffic codes to indicate future left/right turns and stop maneuvers with arm signals. In the case of pedestrians, no indications can be assumed a priori. Instead, we hypothesize that the walking pattern of a pedestrian can allow us to determine if he/she has the intention of crossing the road in the path of the egovehicle, so that the ego-vehicle must maneuver accordingly (e.g. slowing down or stopping). In this PhD work, we show how the same methodology can be used for recognizing pedestrians and cyclists’ intentions. For pedestrians, we perform experiments on the publicly available Daimler and JAAD datasets. For cyclists, we did not found an analogous dataset, therefore, we created our own one by acquiring
and annotating corresponding video-sequences which we aim to share with the
research community. Overall, the proposed pipeline provides new state-of-the-art results on the intention recognition of VRUs.

Abstract: Humansmove their eyes in order to learn visual representations of the world. These eye movements depend on distinct factors, either by the scene that we perceive or by our own decisions. To select what is relevant to attend is part of our survival mechanisms and the way we build reality, as we constantly react both consciously and unconsciously to all the stimuli that is projected into our eyes. In this thesis we try to explain (1) how we move our eyes, (2) how to build machines that understand visual information and deploy eyemovements, and (3) how to make these machines understand tasks in order to decide for eye movements.
(1) We provided the analysis of eye movement behavior elicited by low-level feature distinctiveness with a dataset of 230 synthetically-generated image patterns. A total of 15 types of stimuli has been generated (e.g. orientation, brightness, color, size, etc.), with 7 feature contrasts for each feature category. Eye-tracking data was collected from 34 participants during the viewing of the dataset, using Free-Viewing and Visual Search task instructions. Results showed that saliency is predominantly and distinctively influenced by: 1. feature type, 2. feature contrast, 3. Temporality of fixations, 4. task difficulty and 5. center bias. From such dataset (SID4VAM), we have computed a benchmark of saliency models by testing performance using psychophysical patterns. Model performance has been evaluated considering model inspiration and consistency with human psychophysics. Our study reveals that state-of-the-art Deep Learning saliency models do not performwell with synthetic pattern images, instead, modelswith Spectral/Fourier inspiration outperform others in saliency metrics and are more consistent with human psychophysical experimentation.
(2) Computations in the primary visual cortex (area V1 or striate cortex) have long been hypothesized to be responsible, among several visual processing mechanisms, of bottom-up visual attention (also named saliency). In order to validate this hypothesis, images from eye tracking datasets have been processed with a biologically plausible model of V1 (named Neurodynamic SaliencyWaveletModel or NSWAM). Following Li’s neurodynamic model, we define V1’s lateral connections with a network of firing rate neurons, sensitive to visual features such as brightness, color, orientation and scale. Early subcortical processes (i.e. retinal and thalamic) are functionally simulated. The resulting saliency maps are generated from the model output, representing the neuronal activity of V1 projections towards brain areas involved in eye movement control. We want to pinpoint that our unified computational architecture is able to reproduce several visual processes (i.e. brightness, chromatic induction and visual discomfort) without applying any type of training or optimization and keeping the same parametrization. The model has been extended (NSWAM-CM) with an implementation of the cortical magnification function to define the retinotopical projections towards V1, processing neuronal activity for each distinct view during scene observation. Novel computational definitions of top-down inhibition (in terms of inhibition of return and selection mechanisms), are also proposed to predict attention in Free-Viewing and Visual Search conditions. Results show that our model outperforms other biologically-inpired models of saliency prediction as well as to predict visual saccade sequences, specifically for nature and synthetic images. We also show how temporal and spatial characteristics of inhibition of return can improve prediction of saccades, as well as how distinct search strategies (in terms of feature-selective or category-specific inhibition) predict attention at distinct image contexts.
(3) Although previous scanpath models have been able to efficiently predict saccades during Free-Viewing, it is well known that stimulus and task instructions can strongly affect eye movement patterns. In particular, task priming has been shown to be crucial to the deployment of eye movements, involving interactions between brain areas related to goal-directed behavior, working and long-termmemory in combination with stimulus-driven eyemovement neuronal correlates. In our latest study we proposed an extension of the Selective Tuning Attentive Reference Fixation ControllerModel based on task demands (STAR-FCT), describing novel computational definitions of Long-TermMemory, Visual Task Executive and Task Working Memory. With these modules we are able to use textual instructions in order to guide the model to attend to specific categories of objects and/or places in the scene. We have designed our memorymodel by processing a visual hierarchy of low- and high-level features. The relationship between the executive task instructions and the memory representations has been specified using a tree of semantic similarities between the learned features and the object category labels. Results reveal that by using this model, the resulting object localizationmaps and predicted saccades have a higher probability to fall inside the salient regions depending on the distinct task instructions compared to saliency.

Abstract: Lung cancer is one of the most diagnosed cancers among men and women. Actually,
lung cancer accounts for 13% of the total cases with a 5-year global survival
rate in patients. Although Early detection increases survival rate from 38% to 67%, accurate diagnosis remains a challenge. Pathological confirmation requires extracting a sample of the lesion tissue for its biopsy. The preferred procedure for tissue biopsy is called bronchoscopy. A bronchoscopy is an endoscopic technique for the internal exploration of airways which facilitates the performance of minimal invasive interventions with low risk for the patient. Recent advances in bronchoscopic devices have increased their use for minimal invasive diagnostic and intervention procedures, like lung cancer biopsy sampling. Despite the improvement in bronchoscopic device quality, there is a lack of intelligent computational systems for supporting in-vivo clinical decision during examinations. Existing technologies fail to accurately reach the lesion due to several aspects at intervention off-line planning and poor intra-operative guidance at exploration time. Existing guiding systems radiate patients and clinical staff,might be expensive and achieve a suboptimlal 70% of yield boost. Diagnostic yield could be improved reducing radiation and costs by developing intra-operative support systems able to guide the bronchoscopist to the lesion during the intervention. The goal of this PhD thesis is to develop an image-based navigation systemfor intra-operative guidance of bronchoscopists to a target lesion across a path previously planned on a CT-scan. We propose a 3D navigation system which uses the anatomy of video bronchoscopy frames to locate the bronchoscope within the airways. Once the bronchoscope is located, our navigation system is able to indicate the bifurcation which needs to be followed to reach the lesion. In order to facilitate an off-line validation
as realistic as possible, we also present a method for augmenting simulated virtual bronchoscopies with the appearance of intra-operative videos. Experiments performed on augmented and intra-operative videos, prove that our algorithm can be speeded up for an on-line implementation in the operating room.

Abstract: One of the fundamental problems of computer vision is to represent images with compact semantically relevant embeddings. These embeddings could then be used in a wide variety of applications, such as image retrieval, object detection, and video search. The main objective of this thesis is to study image embeddings from two aspects: color embeddings and deep embeddings.
In the first part of the thesis we start from hand-crafted color embeddings. We propose a method to order the additional color names according to their complementary nature with the basic eleven color names. This allows us to compute color name representations with high discriminative power of arbitrary length. Psychophysical experiments confirm that our proposed method outperforms baseline approaches. Secondly, we learn deep color embeddings from weakly labeled data by adding an attention strategy. The attention branch is able to correctly identify the relevant regions for each class. The advantage of our approach is that it can learn color names for specific domains for which no pixel-wise labels exists.
In the second part of the thesis, we focus on deep embeddings. Firstly, we address the problem of compressing large embedding networks into small networks, while maintaining similar performance. We propose to distillate the metrics from a teacher network to a student network. Two new losses are introduced to model the communication of a deep teacher network to a small student network: one based on an absolute teacher, where the student aims to produce the same embeddings as the teacher, and one based on a relative teacher, where the distances between pairs of data points is communicated from the teacher to the student. In addition, various aspects of distillation have been investigated for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. Finally, another aspect of deep metric learning, namely lifelong learning, is studied. We observed some drift occurs during training of new tasks for metric learning. A method to estimate the semantic drift based on the drift which is experienced by data of the current task during its training is introduced. Having this estimation, previous tasks can be compensated for this drift, thereby improving their performance. Furthermore, we show that embedding networks suffer significantly less from catastrophic forgetting compared to classification networks when learning new tasks.