Abstract: Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labor intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image.

Abstract: Counterfeiting and piracy are a form of theft that has been steadily growing in recent years. A counterfeit is an unauthorized reproduction of an authentic/genuine object. Banknotes and identity documents are two common objects of counterfeiting. The former is used by organized criminal groups to finance a variety of illegal activities or even to destabilize entire countries due the inflation effect. Generally, in order to run their illicit businesses, counterfeiters establish companies and bank accounts using fraudulent identity documents. The illegal activities generated by counterfeit banknotes and identity documents has a damaging effect on business, the economy and the general population. To fight against counterfeiters, governments and authorities around the globe cooperate and develop security features to protect their security documents. Many of the security features in identity documents can also be found in banknotes. In this dissertation we focus our efforts in detecting the counterfeit banknotes and identity documents by analyzing the security features at the background printing. Background areas on secure documents contain fine-line patterns and designs that are difficult to reproduce without the manufacturers cutting-edge printing equipment. Our objective is to find the loose of resolution between the genuine security document and the printed counterfeit version with a publicly available commercial printer. We first present the most complete survey to date in identity and banknote security features. The compared algorithms and systems are based on computer vision and machine learning. Then we advance to present the banknote and identity counterfeit dataset we have built and use along all this thesis. Afterwards, we evaluate and adapt algorithms in the literature for the security background texture analysis. We study this problem from the point of view of robustness, computational efficiency and applicability into a real and non-controlled industrial scenario, proposing key insights to use these algorithms. Next, within the industrial environment of this thesis, we build a complete service oriented architecture to detect counterfeit documents. The mobile application and the server framework intends to be used even by non-expert document examiners to spot counterfeits. Later, we re-frame the problem of background texture counterfeit detection as a full-reference game of spotting the differences, by alternating glimpses between a counterfeit and a genuine background using recurrent neural networks. Finally, we deal with the lack of counterfeit samples, studying different approaches based on anomaly detection.

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: Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have considered to integrate the visual and audio modalities for this purpose. In this work, we propose a multimodal approach for egocentric action recognition in a kitchen environment that relies on audio and visual information. Our model combines a sparse temporal sampling strategy with a late fusion of audio, spatial, and temporal streams. Experimental results on the EPIC-Kitchens dataset show that multimodal integration leads to better performance than unimodal approaches. In particular, we achieved a 5.18% improvement over the state of the art on verb classification.

Abstract: Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting highlevel semantic information present in images as textual cues in the Visual Question Answering process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.

Abstract: This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not addressed
by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image. The competition introduces a new dataset comprising 23, 038 images annotated with 31, 791 question / answer pairs where the answer is always grounded on text instances present in the image. The images are taken from 7 different public computer vision datasets, covering a wide range of scenarios.
The competition was structured in three tasks of increasing difficulty, that require reading the text in a scene and understanding it in the context of the scene, to correctly answer a given question. A novel evaluation metric is presented, which elegantly assesses both key capabilities expected from an optimal model: text recognition and image understanding. A detailed analysis of results from different participants is showcased, which provides insight into the current capabilities of VQA systems that can read. We firmly believe the dataset proposed in this challenge will be an important milestone to consider towards a path of more robust and general models that
can exploit scene text to achieve holistic image understanding.

Abstract: One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images.

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.