Augmented Audiovisual Translation: the Perks and Perils of the Implementation of Artificial Intelligence in Subtitling and Dubbing

This thesis examines the state of audiovisual translation (AVT) in the aftermath of the COVID-19 emergency, highlighting new trends with regards to the implementation of AI technologies as well as their strengths, constraints, and ethical implications. It starts with an overview of the current AVT landscape, focusing on future projections about its evolution and its critical aspects such as the worsening working conditions lamented by AVT professionals – especially freelancers – in recent years and how they might be affected by the advent of AI technologies in the industry. The second chapter delves into the history and development of three AI technologies which are used in combination with neural machine translation in automatic AVT tools: automatic speech recognition, speech synthesis and deepfakes (voice cloning and visual deepfakes for lip syncing), including real examples of start-up companies that utilize them – or are planning to do so – to localize audiovisual content automatically or semi-automatically. The third chapter explores the many ethical concerns around these innovative technologies, which extend far beyond the field of translation; at the same time, it attempts to revindicate their potential to bring about immense progress in terms of accessibility and international cooperation, provided that their use is properly regulated. Lastly, the fourth chapter describes two experiments, testing the efficacy of the currently available tools for automatic subtitling and automatic dubbing respectively, in order to take a closer look at their perks and limitations compared to more traditional approaches. This analysis aims to help discerning legitimate concerns from unfounded speculations with regards to the AI technologies which are entering the field of AVT; the intention behind it is to humbly suggest a constructive and optimistic view of the technological transformations that appear to be underway, whilst also acknowledging their potential risks.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Non-evolutive pattern recognition techniques: An application in medical image diagnostics

Lo studio dell’intelligenza artificiale si pone come obiettivo la risoluzione di una classe di problemi che richiedono processi cognitivi difficilmente codificabili in un algoritmo per essere risolti. Il riconoscimento visivo di forme e figure, l’interpretazione di suoni, i giochi a conoscenza incompleta, fanno capo alla capacità umana di interpretare input parziali come se fossero completi, e di agire di conseguenza. Nel primo capitolo della presente tesi sarà costruito un semplice formalismo matematico per descrivere l’atto di compiere scelte. Il processo di “apprendimento” verrà descritto in termini della massimizzazione di una funzione di prestazione su di uno spazio di parametri per un ansatz di una funzione da uno spazio vettoriale ad un insieme finito e discreto di scelte, tramite un set di addestramento che descrive degli esempi di scelte corrette da riprodurre. Saranno analizzate, alla luce di questo formalismo, alcune delle più diffuse tecniche di artificial intelligence, e saranno evidenziate alcune problematiche derivanti dall’uso di queste tecniche. Nel secondo capitolo lo stesso formalismo verrà applicato ad una ridefinizione meno intuitiva ma più funzionale di funzione di prestazione che permetterà, per un ansatz lineare, la formulazione esplicita di un set di equazioni nelle componenti del vettore nello spazio dei parametri che individua il massimo assoluto della funzione di prestazione. La soluzione di questo set di equazioni sarà trattata grazie al teorema delle contrazioni. Una naturale generalizzazione polinomiale verrà inoltre mostrata. Nel terzo capitolo verranno studiati più nel dettaglio alcuni esempi a cui quanto ricavato nel secondo capitolo può essere applicato. Verrà introdotto il concetto di grado intrinseco di un problema. Verranno inoltre discusse alcuni accorgimenti prestazionali, quali l’eliminazione degli zeri, la precomputazione analitica, il fingerprinting e il riordino delle componenti per lo sviluppo parziale di prodotti scalari ad alta dimensionalità. Verranno infine introdotti i problemi a scelta unica, ossia quella classe di problemi per cui è possibile disporre di un set di addestramento solo per una scelta. Nel quarto capitolo verrà discusso più in dettaglio un esempio di applicazione nel campo della diagnostica medica per immagini, in particolare verrà trattato il problema della computer aided detection per il rilevamento di microcalcificazioni nelle mammografie.

Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

Deep learning models for the automatic analysis of volleyball plays

Collecting and analysing data is an important element in any field of human activity and research. Even in sports, collecting and analyzing statistical data is attracting a growing interest. Some exemplar use cases are: improvement of technical/tactical aspects for team coaches, definition of game strategies based on the opposite team play or evaluation of the performance of players. Other advantages are related to taking more precise and impartial judgment in referee decisions: a wrong decision can change the outcomes of important matches. Finally, it can be useful to provide better representations and graphic effects that make the game more engaging for the audience during the match. Nowadays it is possible to delegate this type of task to automatic software systems that can use cameras or even hardware sensors to collect images or data and process them. One of the most efficient methods to collect data is to process the video images of the sporting event through mixed techniques concerning machine learning applied to computer vision. As in other domains in which computer vision can be applied, the main tasks in sports are related to object detection, player tracking, and to the pose estimation of athletes. The goal of the present thesis is to apply different models of CNNs to analyze volleyball matches. Starting from video frames of a volleyball match, we reproduce a bird's eye view of the playing court where all the players are projected, reporting also for each player the type of action she/he is performing.

Automatic detection of the inferior alveolar nerve in CT scans with CenterNet

The inferior alveolar nerve (IAN) lies within the mandibular canal, named inferior alveolar canal in literature. The detection of this nerve is important during maxillofacial surgeries or for creating dental implants. The poor quality of cone-beam computed tomography (CBCT) and computed tomography (CT) scans and/or bone gaps within the mandible increase the difficulty of this task, posing a challenge to human experts who are going to manually detect it and resulting in a time-consuming task.Therefore this thesis investigates two methods to automatically detect the IAN: a non-data driven technique and a deep-learning method. The latter tracks the IAN position at each frame leveraging detections obtained with the deep neural network CenterNet, fined-tuned for our task, and temporal and spatial information.

Machine learning "as a service" for high energy physics (MLaaS4HEP): evolution of a framework for ML-based physics analyses

The scientific success of the LHC experiments at CERN highly depends on the availability of computing resources which efficiently store, process, and analyse the amount of data collected every year. This is ensured by the Worldwide LHC Computing Grid infrastructure that connect computing centres distributed all over the world with high performance network. LHC has an ambitious experimental program for the coming years, which includes large investments and improvements both for the hardware of the detectors and for the software and computing systems, in order to deal with the huge increase in the event rate expected from the High Luminosity LHC (HL-LHC) phase and consequently with the huge amount of data that will be produced. Since few years the role of Artificial Intelligence has become relevant in the High Energy Physics (HEP) world. Machine Learning (ML) and Deep Learning algorithms have been successfully used in many areas of HEP, like online and offline reconstruction programs, detector simulation, object reconstruction, identification, Monte Carlo generation, and surely they will be crucial in the HL-LHC phase. This thesis aims at contributing to a CMS R&D project, regarding a ML "as a Service" solution for HEP needs (MLaaS4HEP). It consists in a data-service able to perform an entire ML pipeline (in terms of reading data, processing data, training ML models, serving predictions) in a completely model-agnostic fashion, directly using ROOT files of arbitrary size from local or distributed data sources. This framework has been updated adding new features in the data preprocessing phase, allowing more flexibility to the user. Since the MLaaS4HEP framework is experiment agnostic, the ATLAS Higgs Boson ML challenge has been chosen as physics use case, with the aim to test MLaaS4HEP and the contribution done with this work.

Variational Quantum Splines: Moving Beyond Linearity for Quantum Activation Functions

Activation functions within neural networks play a crucial role in Deep Learning since they allow to learn complex and non-trivial patterns in the data. However, the ability to approximate non-linear functions is a significant limitation when implementing neural networks in a quantum computer to solve typical machine learning tasks. The main burden lies in the unitarity constraint of quantum operators, which forbids non-linearity and poses a considerable obstacle to developing such non-linear functions in a quantum setting. Nevertheless, several attempts have been made to tackle the realization of the quantum activation function in the literature. Recently, the idea of the QSplines has been proposed to approximate a non-linear activation function by implementing the quantum version of the spline functions. Yet, QSplines suffers from various drawbacks. Firstly, the final function estimation requires a post-processing step; thus, the value of the activation function is not available directly as a quantum state. Secondly, QSplines need many error-corrected qubits and a very long quantum circuits to be executed. These constraints do not allow the adoption of the QSplines on near-term quantum devices and limit their generalization capabilities. This thesis aims to overcome these limitations by leveraging hybrid quantum-classical computation. In particular, a few different methods for Variational Quantum Splines are proposed and implemented, to pave the way for the development of complete quantum activation functions and unlock the full potential of quantum neural networks in the field of quantum machine learning.

Dataset Fusion application on deep learning Object Detection task

Application of dataset fusion techniques to an object detection task, involving the use of deep learning as convolutional neural networks, to manage to create a single RCNN architecture able to inference with good performances on two distinct datasets with different domains.

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.

Depth Estimation in Stereo Biomedical Images via Proxy-Supervised Deep Learning

In order to estimate depth through supervised deep learning-based stereo methods, it is necessary to have access to precise ground truth depth data. While the gathering of precise labels is commonly tackled by deploying depth sensors, this is not always a viable solution. For instance, in many applications in the biomedical domain, the choice of sensors capable of sensing depth at small distances with high precision on difficult surfaces (that present non-Lambertian properties) is very limited. It is therefore necessary to find alternative techniques to gather ground truth data without having to rely on external sensors. In this thesis, two different approaches have been tested to produce supervision data for biomedical images. The first aims to obtain input stereo image pairs and disparities through simulation in a virtual environment, while the second relies on a non-learned disparity estimation algorithm in order to produce noisy disparities, which are then filtered by means of hand-crafted confidence measures to create noisy labels for a subset of pixels. Among the two, the second approach, which is referred in literature as proxy-labeling, has shown the best results and has even outperformed the non-learned disparity estimation algorithm used for supervision.

Convolutional Neural Network Architectures for Template Matching

The Neural Networks customized and tested in this thesis (WaldoNet, FlowNet and PatchNet) are a first exploration and approach to the Template Matching task. The possibilities of extension are therefore many and some are proposed below. During my thesis, I have analyzed the functioning of the classical algorithms and adapted with deep learning algorithms. The features extracted from both the template and the query images resemble the keypoints of the SIFT algorithm. Then, instead of similarity function or keypoints matching, WaldoNet and PatchNet use the convolutional layer to compare the features, while FlowNet uses the correlational layer. In addition, I have identified the major challenges of the Template Matching task (affine/non-affine transformations, intensity changes...) and solved them with a careful design of the dataset.

Integrazione di reti neurali con approcci simbolici per problemi di ragionamento deduttivo in linguaggio naturale

Uno degli obiettivi più ambizioni e interessanti dell'informatica, specialmente nel campo dell'intelligenza artificiale, consiste nel raggiungere la capacità di far ragionare un computer in modo simile a come farebbe un essere umano. I più recenti successi nell'ambito delle reti neurali profonde, specialmente nel campo dell'elaborazione del testo in linguaggio naturale, hanno incentivato lo studio di nuove tecniche per affrontare tale problema, a cominciare dal ragionamento deduttivo, la forma più semplice e lineare di ragionamento logico. La domanda fondamentale alla base di questa tesi è infatti la seguente: in che modo una rete neurale basata sull'architettura Transformer può essere impiegata per avanzare lo stato dell'arte nell'ambito del ragionamento deduttivo in linguaggio naturale? Nella prima parte di questo lavoro presento uno studio approfondito di alcune tecnologie recenti che hanno affrontato questo problema con intuizioni vincenti. Da questa analisi emerge come particolarmente efficace l'integrazione delle reti neurali con tecniche simboliche più tradizionali. Nella seconda parte propongo un focus sull'architettura ProofWriter, che ha il pregio di essere relativamente semplice e intuitiva pur presentando prestazioni in linea con quelle dei concorrenti. Questo approfondimento mette in luce la capacità dei modelli T5, con il supporto del framework HuggingFace, di produrre più risposte alternative, tra cui è poi possibile cercare esternamente quella corretta. Nella terza e ultima parte fornisco un prototipo che mostra come si può impiegare tale tecnica per arricchire i sistemi tipo ProofWriter con approcci simbolici basati su nozioni linguistiche, conoscenze specifiche sul dominio applicativo o semplice buonsenso. Ciò che ne risulta è un significativo miglioramento dell'accuratezza rispetto al ProofWriter originale, ma soprattutto la dimostrazione che è possibile sfruttare tale capacità dei modelli T5 per migliorarne le prestazioni.

Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.