The recent progress in artificial neural networks (rebranded as “deep learning”) has significantly boosted the state-of-the-art in numerous domains of computer vision offering an opportunity to approach the problems which were hardly solvable with conventional machine learning. Thus, in the frame of this PhD study, we explore how deep learning techniques can help in the analysis of one the most basic and essential semantic traits revealed by a human face, namely, gender and age. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes. Convolutional Neural Network (CNN) has currently become a standard model for image-based object recognition in general, and therefore, is a natural choice for addressing the first of these two problems. However, our preliminary studies have shown that the ...

When listening to music, some humans can easily recognize which instruments play at what time or when a new musical segment starts, but cannot describe exactly how they do this. To automatically describe particular aspects of a music piece – be it for an academic interest in emulating human perception, or for practical applications –, we can thus not directly replicate the steps taken by a human. We can, however, exploit that humans can easily annotate examples, and optimize a generic function to reproduce these annotations. In this thesis, I explore solving different music perception tasks with deep learning, a recent branch of machine learning that optimizes functions of many stacked nonlinear operations – referred to as deep neural networks – and promises to obtain better results or require less domain knowledge than more traditional techniques. In particular, I employ ...

In recent years Machine Learning and in particular Deep Learning have excelled in object recognition and classification tasks in computer vision. As these methods extract features from the data itself by learning features that are relevant for a particular task, a key aspect of this remarkable success is the amount of data on which these methods train. Biomedical applications face the problem that the amount of training data is limited. In particular, labels and annotations are usually scarce and expensive to obtain as they require biological or medical expertise. One way to overcome this issue is to use additional knowledge about the data at hand. This guidance can come from expert knowledge, which puts focus on specific, relevant characteristics in the images, or geometric priors which can be used to exploit the spatial relationships in the images. This thesis presents ...

In recent years, a huge body of data generated by various applications in domains like social networks and healthcare have paved the way for the development of high performance models. Deep learning has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks. Combined with advancements in electromyography it has given rise to new hand gesture recognition applications, such as human computer interfaces, sign language recognition, robotics control and rehabilitation games. The purpose of this thesis is to develop novel methods for electromyography signal analysis based on deep learning for the problem of hand gesture recognition. Specifically, we focus on methods for data preparation and developing accurate models even when few data are available. Electromyography signals are in general one-dimensional time-series with a rich frequency content. Various feature sets have ...

The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this thesis, we address the challenges of knowledge transfer through embedding spaces that capture and store hierarchical knowledge. In the first part of the thesis, we focus on the problem of cross-domain knowledge transfer. We first address zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We train two coupled dictionaries which align visual and semantic domains via an intermediate embedding space. We then extend this idea by training deep networks that ...

Over the last few years, i-vectors have been the state-of-the-art technique in speaker and language recognition. Recent advances in Deep Learning (DL) technology have improved the quality of i-vectors but the DL techniques in use are computationally expensive and need speaker or/and phonetic labels for the background data, which are not easily accessible in practice. On the other hand, the lack of speaker-labeled background data makes a big performance gap, in speaker recognition, between two well-known cosine and Probabilistic Linear Discriminant Analysis (PLDA) i-vector scoring techniques. It has recently been a challenge how to fill this gap without speaker labels, which are expensive in practice. Although some unsupervised clustering techniques are proposed to estimate the speaker labels, they cannot accurately estimate the labels. This thesis tries to solve the problems above by using the DL technology in different ways, without ...

Human Activity Recognition HAR has been a hot research topic in the last decade due to its wide range of applications. Indeed, it has been the basis for implementa- tion of many computer vision applications, home security, video surveillance, and human-computer interaction. We intend by HAR, tools, and systems allowing to detect and recognize actions performed by individuals. With the considerable progress made in sensing technologies, HAR systems shifted from wearable and ambient-based to vision-based. This motivated the researchers to propose a large mass of vision-based solutions. From another perspective, HAR plays an impor- tant role in the health care sector and gets involved in the construction of fall detection systems and many smart home-related systems. Fall detection FD con- sists in identifying the occurrence of falls among other daily life activities. This is essential because falling is one of ...

This thesis contributes to motion characterization through inertial and physiological signals captured by wearable devices and analyzed using signal processing and deep learning techniques. This research leverages the possibilities of motion analysis for three main applications: to know what physical activity a person is performing (Human Activity Recognition), to identify who is performing that motion (user identification) or know how the movement is being performed (motor anomaly detection). Most previous research has addressed human motion modeling using invasive sensors in contact with the user or intrusive sensors that modify the user’s behavior while performing an action (cameras or microphones). In this sense, wearable devices such as smartphones and smartwatches can collect motion signals from users during their daily lives in a less invasive or intrusive way. Recently, there has been an exponential increase in research focused on inertial-signal processing to ...

The recent success of deep learning is conditioned on the availability of large annotated datasets for supervised learning. Data annotation, however, is a laborious and a time-consuming task. When a model fully trained on an annotated source domain is applied to a target domain with different data distribution, a greatly diminished generalization performance can be observed due to domain shift. Unsupervised Domain Adaptation (UDA) aims to mitigate the impact of domain shift when the target domain is unannotated. The majority of UDA algorithms assume joint access between source and target data, which may violate data privacy restrictions in many real world applications. In this thesis I propose source-free UDA approaches that are well suited for scenarios when source and target data are only accessible sequentially. I show that across several application domains, for the adaptation process to be successful it ...

The subject of this PhD thesis is the efficient and robust processing and analysis of the audio recordings that are derived from a call center. The thesis is comprised of two parts. The first part is dedicated to dialogue/non-dialogue detection and to speaker segmentation. The systems that are developed are prerequisite for detecting (i) the audio segments that actually contain a dialogue between the system and the call center customer and (ii) the change points between the system and the customer. This way the volume of the audio recordings that need to be processed is significantly reduced, while the system is automated. To detect the presence of a dialogue several systems are developed. This is the first effort found in the international literature that the audio channel is exclusively exploited. Also, it is the first time that the speaker utterance ...

The ultimate aim of research into computer vision is designing a system which interprets its surrounding environment in a similar way the human can do effortlessly. However, the state of technology is far from achieving such a goal. In this thesis different components of a computer vision system that are designed for the task of interpreting man-made scenes, in particular images of buildings, are described. The flow of information in the proposed system is bottom-up i.e., the image is first segmented into its meaningful components and subsequently the regions are labelled using a contextual classifier. Starting from simple observations concerning the human vision system and the gestalt laws of human perception, like the law of 'good (simple) shape' and 'perceptual grouping', a blob detector is developed, that identifies components in a 2D image. These components are convex regions of interest, ...

The advent of multi-microphone setups on a plethora of commercial devices in recent years has generated a newfound interest in the development of robust microphone array signal processing methods. These methods are generally used to either estimate parameters associated with acoustic scene or to extract signal(s) of interest. In most practical scenarios, the sources are located in the far-field of a microphone array where the main spatial information of interest is the direction-of-arrival (DOA) of the plane waves originating from the source positions. The focus of this thesis is to incorporate robustness against either lack of or imperfect/erroneous information regarding the DOAs of the sound sources within a microphone array signal processing framework. The DOAs of sound sources is by itself important information, however, it is most often used as a parameter for a subsequent processing method. One of the ...

Ill-posed inverse problems appear in many signal and image processing applications, such as deblurring, super-resolution and compressed sensing. The common approach to address them is to design a specific algorithm, or recently, a specific deep neural network, for each problem. Both signal processing and machine learning tactics have drawbacks: traditional reconstruction strategies exhibit limited performance for complex signals, such as natural images, due to the hardness of their mathematical modeling; while modern works that circumvent signal modeling by training deep convolutional neural networks (CNNs) suffer from a huge performance drop when the observation model used in training is inexact. In this work, we develop and analyze reconstruction algorithms that are not restricted to a specific signal model and are able to handle different observation models. Our main contributions include: (a) We generalize the popular sparsity-based CoSaMP algorithm to any signal ...

Advances in compression techniques, decreasing cost of storage, and high-speed transmission have facilitated the way videos are created, stored and distributed. As a consequence, videos are now being used in many applications areas. The increase in the amount of video data deployed and used in today's applications reveals not only the importance as multimedia data type, but also led to the requirement of efficient management of video data. This management paved the way for new research areas, such as indexing and retrieval of video with respect to their spatio-temporal, visual and semantic contents. This thesis presents work towards a unified framework for semi-automated video indexing and interactive retrieval. To create an efficient index, a set of representative key frames are selected which capture and encapsulate the entire video content. This is achieved by, firstly, segmenting the video into its constituent ...

Estimating object motion is one of the key components of video processing and the first step in applications which require video representation. Visual object tracking is one way of extracting this component, and it is one of the major problems in the field of computer vision. Numerous discriminative and generative machine learning approaches have been employed to solve this problem. Recently, correlation filter based (CFB) approaches have been popular due to their computational efficiency and notable performances on benchmark datasets. The ultimate goal of CFB approaches is to find a filter (i.e., template) which can produce high correlation outputs around the actual object location and low correlation outputs around the locations that are far from the object. Nevertheless, CFB visual tracking methods suffer from many challenges, such as occlusion, abrupt appearance changes, fast motion and object deformation. The main reasons ...