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.

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.

ICE Emissions Estimation through Machine-learning techniques to support real-world R&D experiments

The emissions estimation, both during homologation and standard driving, is one of the new challenges that automotive industries have to face. The new European and American regulation will allow a lower and lower quantity of Carbon Monoxide emission and will require that all the vehicles have to be able to monitor their own pollutants production. Since numerical models are too computationally expensive and approximated, new solutions based on Machine Learning are replacing standard techniques. In this project we considered a real V12 Internal Combustion Engine to propose a novel approach pushing Random Forests to generate meaningful prediction also in extreme cases (extrapolation, very high frequency peaks, noisy instrumentation etc.). The present work proposes also a data preprocessing pipeline for strongly unbalanced datasets and a reinterpretation of the regression problem as a classification problem in a logarithmic quantized domain. Results have been evaluated for two different models representing a pure interpolation scenario (more standard) and an extrapolation scenario, to test the out of bounds robustness of the model. The employed metrics take into account different aspects which can affect the homologation procedure, so the final analysis will focus on combining all the specific performances together to obtain the overall conclusions.

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.

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.

Self-supervised information retrieval: a novel approach based on Deep Metric Learning and Neural Language Models

Most of the existing open-source search engines, utilize keyword or tf-idf based techniques to find relevant documents and web pages relative to an input query. Although these methods, with the help of a page rank or knowledge graphs, proved to be effective in some cases, they often fail to retrieve relevant instances for more complicated queries that would require a semantic understanding to be exploited. In this Thesis, a self-supervised information retrieval system based on transformers is employed to build a semantic search engine over the library of Gruppo Maggioli company. Semantic search or search with meaning can refer to an understanding of the query, instead of simply finding words matches and, in general, it represents knowledge in a way suitable for retrieval. We chose to investigate a new self-supervised strategy to handle the training of unlabeled data based on the creation of pairs of ’artificial’ queries and the respective positive passages. We claim that by removing the reliance on labeled data, we may use the large volume of unlabeled material on the web without being limited to languages or domains where labeled data is abundant.

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.

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.

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.

Quality and Aspect based Argument Generation

Natural Language Processing has always been one of the most popular topics in Artificial Intelligence. Argument-related research in NLP, such as argument detection, argument mining and argument generation, has been popular, especially in recent years. In our daily lives, we use arguments to express ourselves. The quality of arguments heavily impacts the effectiveness of our communications with others. In professional fields, such as legislation and academic areas, arguments of good quality play an even more critical role. Therefore, argument generation with good quality is a challenging research task that is also of great importance in NLP. The aim of this work is to investigate the automatic generation of arguments with good quality, according to the given topic, stance and aspect (control codes). To achieve this goal, a module based on BERT [17] which could judge an argument's quality is constructed. This module is used to assess the quality of the generated arguments. Another module based on GPT-2 [19] is implemented to generate arguments. Stances and aspects are also used as guidance when generating arguments. After combining all these models and techniques, the ranks of the generated arguments could be acquired to evaluate the final performance. This dissertation describes the architecture and experimental setup, analyzes the results of our experimentation, and discusses future directions.

SmartForge: An event-driven architecture for simulator-based process optimization

In the metal industry, and more specifically in the forging one, scrap material is a crucial issue and reducing it would be an important goal to reach. Not only would this help the companies to be more environmentally friendly and more sustainable, but it also would reduce the use of energy and lower costs. At the same time, the techniques for Industry 4.0 and the advancements in Artificial Intelligence (AI), especially in the field of Deep Reinforcement Learning (DRL), may have an important role in helping to achieve this objective. This document presents the thesis work, a contribution to the SmartForge project, that was performed during a semester abroad at Karlstad University (Sweden). This project aims at solving the aforementioned problem with a business case of the company Bharat Forge Kilsta, located in Karlskoga (Sweden). The thesis work includes the design and later development of an event-driven architecture with microservices, to support the processing of data coming from sensors set up in the company's industrial plant, and eventually the implementation of an algorithm with DRL techniques to control the electrical power to use in it.

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.

Graph-based Vision-Language Model for Multi-Modal Retrieval of Fashion Products

Artificial Intelligence is reshaping the field of fashion industry in different ways. E-commerce retailers exploit their data through AI to enhance their search engines, make outfit suggestions and forecast the success of a specific fashion product. However, it is a challenging endeavour as the data they possess is huge, complex and multi-modal. The most common way to search for fashion products online is by matching keywords with phrases in the product's description which are often cluttered, inadequate and differ across collections and sellers. A customer may also browse an online store's taxonomy, although this is time-consuming and doesn't guarantee relevant items. With the advent of Deep Learning architectures, particularly Vision-Language models, ad-hoc solutions have been proposed to model both the product image and description to solve this problems. However, the suggested solutions do not exploit effectively the semantic or syntactic information of these modalities, and the unique qualities and relations of clothing items. In this work of thesis, a novel approach is proposed to address this issues, which aims to model and process images and text descriptions as graphs in order to exploit the relations inside and between each modality and employs specific techniques to extract syntactic and semantic information. The results obtained show promising performances on different tasks when compared to the present state-of-the-art deep learning architectures.

Smart sampling approaches for Decision-Focused Learning

Many real-word decision- making problems are defined based on forecast parameters: for example, one may plan an urban route by relying on traffic predictions. In these cases, the conventional approach consists in training a predictor and then solving an optimization problem. This may be problematic since mistakes made by the predictor may trick the optimizer into taking dramatically wrong decisions. Recently, the field of Decision-Focused Learning overcomes this limitation by merging the two stages at training time, so that predictions are rewarded and penalized based on their outcome in the optimization problem. There are however still significant challenges toward a widespread adoption of the method, mostly related to the limitation in terms of generality and scalability. One possible solution for dealing with the second problem is introducing a caching-based approach, to speed up the training process. This project aims to investigate these techniques, in order to reduce even more, the solver calls. For each considered method, we designed a particular smart sampling approach, based on their characteristics. In the case of the SPO method, we ended up discovering that it is only necessary to initialize the cache with only several solutions; those needed to filter the elements that we still need to properly learn. For the Blackbox method, we designed a smart sampling approach, based on inferred solutions.