Abstract: In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-the-art compressed video quality enhancement algorithms.

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: During the last decade vision-based human detection systems have started to play a key rolein multiple applications linked to driver assistance, surveillance, robot sensing and home automation.
Detecting humans is by far one of the most challenging tasks in Computer Vision.
This is mainly due to the high degree of variability in the human appearanceassociated to
the clothing, pose, shape and size. Besides, other factors such as cluttered scenarios, partial occlusions, or environmental conditions can make the detection task even harder.
Most promising methods of the state-of-the-art rely on discriminative learning paradigms which are fed with positive and negative examples. The training data is one of the most
relevant elements in order to build a robust detector as it has to cope the large variability of the target. In order to create this dataset human supervision is required. The drawback at this point is the arduous effort of annotating as well as looking for such claimed variability.
In this PhD thesis we address two recurrent problems in the literature. In the first stage,we aim to reduce the consuming task of annotating, namely, by using computer graphics.
More concretely, we develop a virtual urban scenario for later generating a pedestrian dataset.
Then, we train a detector using this dataset, and finally we assess if this detector can be successfully applied in a real scenario.
In the second stage, we focus on increasing the robustness of our pedestrian detectors
under partial occlusions. In particular, we present a novel occlusion handling approach to increase the performance of block-based holistic methods under partial occlusions. For this purpose, we make use of local experts via a RandomSubspaceMethod (RSM) to handle these cases. If the method infers a possible partial occlusion, then the RSM, based on performance statistics obtained from partially occluded data, is applied. The last objective of this thesis
is to propose a robust pedestrian detector based on an ensemble of local experts. To achieve this goal, we use the random forest paradigm, where the trees act as ensembles an their nodesare the local experts. In particular, each expert focus on performing a robust classification ofa pedestrian body patch. This approach offers computational efficiency and far less design complexity when compared to other state-of-the-artmethods, while reaching better accuracy

Abstract: Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time.
We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost.
Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of parameters to be added for each new task. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias.
Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.

Abstract: With an ageing population, the issue of care provision is becoming increasingly important. The simple aspiration of the majority of older people is to live safely and well at home. Housing will be part of health & care integration in the following years and decades. A higher proportion of people will have to rely on informal care through family, friends, neighbors and others who
provide care to an older person in need of assistance (around 80% of care across the EU). They do not usually have a formal status and are usually unpaid. We need to ensure that all disabled or chronically ill people can get the help they need without overburdening their families.
The physical and emotional stress of carers is one of the dangers that this dependency can bring. To prevent carers burnout it is necessary to provide new solutions that are affordable and user friendly for the families and caregivers.