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 ...

Recent advances in many fields ranging from engineering to natural science, require increasingly complicated optimization tasks in the experiment design, for which the target objectives are generally in the form of black-box functions that are expensive to evaluate. In a common formulation of this problem, a designer is expected to solve the black-box optimization tasks via sequentially attempting candidate solutions and receiving feedback from the system. This thesis considers Bayesian optimization (BO) as the black-box optimization framework, and investigates the enhancements on BO from the aspects of efficiency, adaptation and reliability. Generally, BO consists of a surrogate model for providing probabilistic inference and an acquisition function which leverages the probabilistic inference for selecting the next candidate solution. Gaussian process (GP) is a prominent non-parametric surrogate model, and the quality of its inference is a critical factor on the optimality performance ...

This dissertation explores the intersection of data fusion, federated learning, and Bayesian methods, with a focus on their applications in indoor localization, GNSS, and image processing. Data fusion involves integrating data and knowledge from multiple sources. It becomes essential when data is only available in a distributed fashion or when different sensors are used to infer a quantity of interest. Data fusion typically includes raw data fusion, feature fusion, and decision fusion. In this thesis, we will concentrate on feature fusion. Distributed data fusion involves merging sensor data from different sources to estimate an unknown process. Bayesian framework is often used because it can provide an optimal and explainable feature by preserving the full distribution of the unknown given the data, called posterior, over the estimated process at each agent. This allows for easy and recursive merging of sensor data ...

The first part of this dissertation considers distributed learning problems over networked agents. The general objective of distributed adaptation and learning is the solution of global, stochastic optimization problems through localized interactions and without information about the statistical properties of the data. Regularization is a useful technique to encourage or enforce structural properties on the resulting solution, such as sparsity or constraints. A substantial number of regularizers are inherently non-smooth, while many cost functions are differentiable. We propose distributed and adaptive strategies that are able to minimize aggregate sums of objectives. In doing so, we exploit the structure of the individual objectives as sums of differentiable costs and non-differentiable regularizers. The resulting algorithms are adaptive in nature and able to continuously track drifts in the problem; their recursions, however, are subject to persistent perturbations arising from the stochastic nature of ...

Distributed networks comprising a large number of nodes, e.g., Wireless Sensor Networks, Personal Computers (PC’s), laptops, smart phones, etc., which cooperate with each other in order to reach a common goal, constitute a promising technology for several applications. Typical examples include: distributed environmental monitoring, acoustic source localization, power spectrum estimation, etc. Sophisticated cooperation mechanisms can significantly benefit the learning process, through which the nodes achieve their common objective. In this dissertation, the problem of adaptive learning in distributed networks is studied, focusing on the task of distributed estimation. A set of nodes sense information related to certain parameters and the estimation of these parameters constitutes the goal. Towards this direction, nodes exploit locally sensed measurements as well as information springing from interactions with other nodes of the network. Throughout this dissertation, the cooperation among the nodes follows the diffusion optimization ...

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 ...

Detecting anomalous sounds is a difficult task: First, audio data is very high-dimensional and anomalous signal components are relatively subtle in relation to the entire acoustic scene. Furthermore, normal and anomalous audio signals are not inherently different because defining these terms strongly depends on the application. Third, usually only normal data is available for training a system because anomalies are rare, diverse, costly to produce and in many cases unknown in advance. Such a setting is called semi-supervised anomaly detection. In domain-shifted conditions or when only very limited training data is available, all of these problems are even more severe. The goal of this thesis is to overcome these difficulties by teaching an embedding model to learn data representations suitable for semi-supervised anomalous sound detection. More specifically, an anomalous sound detection system is designed such that the resulting representations of ...

Automatic ear recognition systems have seen increased interest over recent years due to multiple desirable characteristics. Ear images used in such systems can typically be extracted from profile head shots or video footage. The acquisition procedure is contactless and non-intrusive, and it also does not depend on the cooperation of the subjects. In this regard, ear recognition technology shares similarities with other image-based biometric modalities. Another appealing property of ear biometrics is its distinctiveness. Recent studies even empirically validated existing conjectures that certain features of the ear are distinct for identical twins. This fact has significant implications for security-related applications and puts ear images on a par with epigenetic biometric modalities, such as the iris. Ear images can also supplement other biometric modalities in automatic recognition systems and provide identity cues when other information is unreliable or even unavailable. In ...

One desideratum in designing cognitive robots is autonomous learning of communication skills, just like humans. The primary step towards this goal is vocabulary acquisition. Being different from the training procedures of the state-of-the-art automatic speech recognition (ASR) systems, vocabulary acquisition cannot rely on prior knowledge of language in the same way. Like what infants do, the acquisition process should be data-driven with multi-level abstraction and coupled with multi-modal inputs. To avoid lengthy training efforts in a word-by-word interactive learning process, a clever learning agent should be able to acquire vocabularies from continuous speech automatically. The work presented in this thesis is entitled \emph{Constrained Non-negative Matrix Factorization for Vocabulary Acquisition from Continuous Speech}. Enlightened by the extensively studied techniques in ASR, we design computational models to discover and represent vocabularies from continuous speech with little prior knowledge of the language to ...

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 effectiveness of machine learning (ML) in today's applications largely depends on the goodness of the representation of data used within the ML algorithms. While the massiveness in dimension of modern day data often requires lower-dimensional data representations in many applications for efficient use of available computational resources, the use of uncorrelated features is also known to enhance the performance of ML algorithms. Thus, an efficient representation learning solution should focus on dimension reduction as well as uncorrelated feature extraction. Even though Principal Component Analysis (PCA) and linear autoencoders are fundamental data preprocessing tools that are largely used for dimension reduction, when engineered properly they can also be used to extract uncorrelated features. At the same time, factors like ever-increasing volume of data or inherently distributed data generation impede the use of existing centralized solutions for representation learning that require ...

In the audio research field, the majority of machine learning systems focus on recognizing a limited number of sound events. However, when a machine interacts with real data, it must be able to handle much more varied and complex situations. To tackle this problem, annotators use natural language, which allows any sound information to be summarized. Automated Audio Captioning (AAC) was introduced recently to develop systems capable of automatically producing a description of any type of sound in text form. This task concerns all kinds of sound events such as environmental, urban, domestic sounds, sound effects, music or speech. This type of system could be used by people who are deaf or hard of hearing, and could improve the indexing of large audio databases. In the first part of this thesis, we present the state of the art of the ...

In the world of Information and communications technology (ICT), strategies for innovation and development are increasingly focusing on applications that require spatial representation and real-time interaction with and within 3D-media environments. One of the major challenges that such applications have to address is user-centricity, reflecting e.g. on developing complexity-hiding services so that people can personalize their own delivery of services. In these terms, multimodal interfaces represent a key factor for enabling an inclusive use of new technologies by everyone. In order to achieve this, multimodal realistic models that describe our environment are needed, and in particular models that accurately describe the acoustics of the environment and communication through the auditory modality are required. Examples of currently active research directions and application areas include 3DTV and future internet, 3D visual-sound scene coding, transmission and reconstruction and teleconferencing systems, to name but ...

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. Furthermore, new challenges arise from modern database architectures, such as the requirements for learning methods to be amenable to streaming, parallel and distributed computing. In this context, an increasingly popular approach is to first compress the database into a representation called a linear sketch, that satisfies all the mentioned requirements, then learn the desired information using only this sketch, which can be significantly faster than using the full data if the sketch is small. In this thesis, we introduce a generic methodology to fit a mixture of probability distributions on the data, using only a sketch of the database. The sketch is defined by combining two notions from the reproducing kernel literature, namely kernel mean embedding and Random Features expansions. It is seen to correspond ...

This thesis investigates the application of language models based on semantic similarity to Automatic Speech Recognition for meetings. We consider data-driven Latent Semantic Analysis based and knowledge-driven WordNet-based models. Latent Semantic Analysis based models are trained for several background domains and it is shown that all background models reduce perplexity compared to the n-gram baseline models, and some background models also significantly improve speech recognition for meetings. A new method for interpolating multiple models is introduced and the relation to cache-based models is investigated. The semantics of the models is investigated through a synonymity task. WordNet-based models are defined for different word-word similarities that use information encoded in the WordNet graph and corpus information. It is shown that these models can significantly improve over baseline random models on the task of word prediction, and that the chosen part-of-speech context is ...