Reserved topic scholarships - 2021 - 1st call
Department of Information Engineering and Computer Science
A1 - Cross-modal understanding and generatIon of visual and textual content (1 grant)
The objective of this research is multimodal generation of visual and textual data: the goal is to achieve a seamless cross-media generation between the different modalities such as text to image, text to video, image to video (i.e., image animation) as well as text from image or video (i.e., captioning). This implies the development of new generative methodologies in a semi-supervised or unsupervised way that allow for a) effective generation of images or videos from textual descriptions in real-time and b) effective generation of textual descriptions from images and video in real time, with input conditioned by an interacting person (e.g., through a visual dialogue) or by the context.
Contact: Niculae Sebe niculae.sebe [at] unitn.it
A2 - Deep Learning for Human Behaviour Analysis in Social Robotics (1 grant)
The research activities related to this PhD position will focus on the study and the implementation of visual data processing algorithms for the analysis of human behaviors in the context of Human Robot Interaction. In particular, the activities will focus on the development of algorithms based on deep learning and in particular, on continual learning and domain adaptation methods, for the recognition of actions and activities in complex scenes. The developed algorithms will be integrated on a humanoid robot. The research activity is supported by the H2020 EU project SPRING.
Contact: Elisa Ricci e.ricci [at] unitn.it
B1 - Low-power Networking and Localization with Ultra-wideband (UWB) (1 grant)
Ultra-wideband (UWB) radios are rapidly gaining popularity, as they can estimate distance (ranging) with great accuracy (<10cm error). This enables countless applications based on proximity and localization, even in GPS-denied environments like indoor. Major vendors like Apple and Samsung have already equipped their latest smartphone models with UWB, which is expected to become as commonplace as WiFi and BLE. The PhD student will explore research themes at the intersection of networking and localization. These include novel schemes to efficiently coordinate and harmonize the two in a single protocol stack, but also novel techniques that improve the two dimensions separately. Particular emphasis will be given to techniques exploiting concurrent transmissions. The activities carried out can be characterized as "systems research". Novel ideas and contributions are embodied in prototypes concretely demonstrating feasibility and improvements over the state of the art. Typical performance metrics include energy efficiency, ranging/positioning accuracy, reliability, and scalability w.r.t. users and sample rate. Models are used to characterize the performance of prototypes, which is then evaluated experimentally in realistic setups. In this respect, the research group offers unique assets, including a 130-node (~8000sqm) indoor UWB testbed and two accurate (mm-level) optical facilities.
Contact: Gian Pietro Picco gianpietro.picco [at] unitn.it
D4 - Development of methodologies and automatic techniques based on artificial intelligence and machine learning for the analysis of data acquired by planetary radars (1 grant)
The research activities are related to planetary radar sounders that are instruments for the study of the subsurface of the Earth and planets . These radars operate from satellite platforms and acquire data related to the subsurface. The research will be focused on the development of a new generation methodologies for the analysis of planetary data that exploit the most recent developments in the framework of artificial intelligence and deep learning. The activity will be related to the definition, design, implementation and validation of automatic techniques for the extraction of the information for the data. Research will be developed at the Remote Sensing Laboratory (https://rslab.disi.unitn.it/) and will be related to the activities in progress on the Radar for Icy Moon Exploration (RIME) on board of the JUpiter ICy moons Explorer (JUICE) of the European Space Agency (see https://sci.esa.int/web/juice) for more details on the mission).
Contact: Lorenzo Bruzzone lorenzo.bruzzone [at] unitn.it
Fondazione Bruno Kessler (FBK)
A3 - Neural Dialogue Models for fighting misinformation and hate speech (1 grant)
Conversational agents are designed to interact with users in multiple domains on several topics using natural language. Recently end-to-end systems have started to be tested to fight fake news and hate speech in single turn settings. Still, scaling to full dialogue interactions is a challenging topic, requiring world and domain knowledge together with a deep understanding of argumentative tactics. The goal of this PhD Thesis is to overcome the shortcomings of traditional end-to-end applications in which all components are trained from the dialogues themselves, by incorporating several dialogues, argumentation and domain features.
Contact: Marco Guerini guerini [at] fbk.eu
A4 - Persona Based neural models for Opinionated Dialogues (1 grant)
In the context of dialogues with chatbots it has been shown that endowing neural models with a persona profile is important to produce more coherent and meaningful conversations. Still, the representation of such personas is still very limited, usually based on simple facts. The goal of this PhD Thesis is to make a step forward, trying to grasp more profound characteristics of human personality (such as opinions, values, and beliefs) to drive language generation of conversational agents in multiple domains and languages.
Contact: Marco Guerini guerini [at] fbk.eu
A5 - End-2-End AI technologies for the semantic interpretation of audio and speech data (1 grant)
End-2-End models for speech recognition have been steadily improved recently, achieving performance comparable to state-of-the-art systems. This paves the way to the adoption of such solutions also for the extraction of semantically higher information, directly from the raw speech. This allows avoiding approaches based on the combination of speech recognition followed by text processing, with consequent propagation of errors from the intermediate stages. The goal of this thesis is to develop innovative end-to-end systems, eventually based on the transformer model and sequence-to-sequence learning, to address tasks like spoken language understanding, named entity recognition, intent classification and so forth. Ideally, at the end of the doctoral thesis, the candidate would have developed a neural audio processing front end that can be applied to a variety of semantic down-stream tasks.
Contact: Giuseppe Daniele Falavigna falavi [at] fbk.eu
A6 - Fairness and explainable methods for machine learning and deep learning algorithms (1 grant)
Machine learning can impact people when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, several works have shown that training data can be unfairly biased against certain populations and groups, for example, those of a particular race, gender, or sexual orientation. Since training data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. This PhD student will work on designing and implementing innovative approaches for fair and explainable machine learning and deep learning algorithms. The selected student will have the possibility of collaborating with the activities of the Human-centric Machine Learning program of the ELLIS society (https://ellis.eu/).
Contact: Bruno Lepri lepri [at] fbk.eu
A7 - Flexibility and Robustness in Speech Translation (1 grant)
The need to translate audio input from one language into text in a target language has dramatically increased in the last few years with the growth of audiovisual content freely available on the Web. Current speech translation (ST) systems are now required to be flexible and robust enough to operate in different application scenarios and diverse working conditions. On one side, the industry calls for key features like real-time processing, domain adaptability, extended language coverage and the capability to adhere to application-specific constraints (e.g. length or lip-synch constraints in the subtitling and dubbing scenarios). On the other side, society calls for new efforts towards inclusiveness with respect to specific categories and groups (e.g. gender-sensitivity, customization to the needs of impaired users). Both dimensions (industry and society) face the orthogonal challenges posed by the variability of audio conditions (e.g. background noise, strong speakers’ accent, overlapping speakers). The objective of this PhD is to advance the state of the art in speech translation to make ST flexible and robust to these and other factors.
Contact: Marco Turchi turchi [at] fbk.eu
B2 - Multi-Access Edge Computing for Beyond 5G Networks (1 grant)
Multi-Access Edge Computing leverages the network's edge to store and process data and applications locally, and provide fast reactions and efficient use of network and computing resources. Future communication systems and networks, both terrestrial and non-terrestrial, will increasingly require solutions based on AI/ML, virtualization and softwarisation techniques besides traditional communication technologies. The goal of this PhD Thesis is to design and explore novel approaches that leverage on close cooperation with these domains from an overall system perspective.
Contact: Cristina Costa ccosta [at] fbk.eu
C1 - Engineering Game-based Motivational Digital System for Personalized and Cooperative Learning (1 grant)
Gamification principles have proven to be very effective in motivating target users in keeping their engagement within everyday challenges, including dedication to education, use of public transportation, adoption of healthy habits, and so forth. School closures due to the COVID-19 pandemic and thus the sudden change in the management of the students' educational pathways has opened up the need for methods and digital systems able to support teachers in defining educational content and objectives for their classrooms and to keep students engaged in their training path. The goal of this PhD Thesis is to investigate approaches, techniques and tools to design and release educational digital systems for personalized and cooperative learning plans. This will be done exploiting AI techniques for adaptive gamification and will support teachers in the process of defining and monitoring dedicated learning plans for their students. At the same time, it will facilitate learning, will encourage motivation and engagement, will improve student’s participation and cooperation, and will stimulate students to expand their knowledge through dedicated learning plans and personalized feedback.
Contact: Antonio Bucchiarone bucchiarone [at] fbk.eu
C2 - Testing for complex parametric systems (1 grant)
The increasing complexity of software systems calls for the development of new methods and tools to design and test software systems characterized by high variability from the point of view of the space of the possible functional configurations, the space of the release architectures, and of the aspects related to dynamic reconfiguration. The goal of this PhD thesis is that of exploring new approaches to the testing, verification and validation of these systems that involve the joint use of model-based and AI based techniques such as planning, machine learning and optimization.
Contact: Angelo Susi susi [at] fbk.eu
C3 - Self-Adaptive Automated Planning and Scheduling via Combination with Reinforcement Learning (1 grant)
Automated Planning is the problem of synthesizing courses of actions guaranteed to achieve the desired objective, given a formal model of the system being controlled. A class of problems particularly interesting for applications is temporal planning (also called planning and scheduling) where the discrete decisions of "what to do" are coupled with the problem of scheduling (deciding "when to do"). Unfortunately, planning and scheduling techniques suffer from scalability issues and are often unable to cope with the complexity of real-word scenarios, despite the plethora of approaches available in the literature. Recently, efforts such as Deepmind AlphaGO and OpenAI Five hit the headlines, with groundbreaking advancements in the field of reinforcement learning. These techniques are able to automatically learn policies to decide what to do in order to achieve the desired goal. However, they offer no formal guarantee and are not model-based. The research objective of this PhD scholarship is to investigate techniques that combine the formal guarantees offered by automated planning and scheduling with the performance and self-improving capabilities offered by recent advances in deep reinforcement learning to construct self-adaptive planners that can improve over time their performance on specific application scenarios.
Contact: Andrea Micheli amicheli [at] fbk.eu
C4 - Formal verification of hybrid system models for control software (1 grant)
Cyber-physical systems are ubiquitous systems that integrate computation, networking and physical processes. The correctness and dependability of their control software are critical in many high-assurance domains such as space, mobility, and energy. However, their design requires hybrid models that combine continuous dynamics with discrete states and is typically verified with simulation-based testing. The objective of this PhD research is that of advancing the state of the art in the formal verification of hybrid system models, integrating various techniques such as SMT-based model checking, simulation, test-case generation, and fault injection. The candidate will work on both theoretical aspects of the problem, as well as its practical applications in relevant case studies, drawn from the domains of aerospace, automotive, railways, and energy.
Contact: Stefano Tonetta tonettas [at] fbk.eu
C5 - Formal verification of complex cyber-physical systems (1 grant) [additional]
Cyber-Physical Systems (CPS) are ubiquitous systems that integrate computation, networking and physical processes. The correctness and dependability of their control software is critical in many high-assurance domains such as space, mobility, and energy. However, their design requires complex component-based hybrid models describing the continuous dynamics of the physical components and the discrete interaction with the control and monitoring components. The objective of this PhD research is that of advancing the state of the art in the formal verification of CPS control design models, integrating various techniques such as SMT-based model checking, contract-based design, abstract interpretation, simulation, test-case generation, and fault injection. The candidate will work on theoretical aspects of the problem as well as its practical applications in relevant case studies, drawn from the domains of aerospace, automotive, railways, and energy.
Contact: Alessandro Cimatti cimatti [at] fbk.eu
D1 - Advanced methodologies for radar and radar sounder image processing (1 grant)
We are looking for candidates willing to develop novel methodologies based on machine learning, deep learning, pattern recognition and artificial intelligence for information extraction, classification, target detection and change detection in radar and radar sounder images. The PhD activity will be developed in the context of the European Space Agency (ESA) space mission JUpiter ICy moons Explorer (JUICE) in the Jovian system. The candidate will be requested to deal with images acquired from active radar systems including Synthetic Aperture Radar (SAR) images and sub-surface radar sounding data from airborne Earth Observation missions and satellite planetary exploration missions. The activity amins in improving the understanding of subsurface structure and their impact on planetary body climate. Besides the requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
- master degree in Electrical Engineering, Communication Engineering, Computer Science, Mathematics or equivalents;
- knowledge in pattern recognition, deep learning, image/signal processing, statistic/remote sensing/radar.
Contact: Francesca Bovolo bovolo [at] fbk.eu
D2 - Remote sensing image time series analysis for climate change (1 grant)
In the context of the green deal transition, we are looking for candidates willing to develop novel methodologies based on machine learning, deep learning pattern recognition and artificial intelligence for information extraction, classification, target detection and change detection in long and dense timeseries of remote sensing images. The candidate will be requested to deal with both multi-/hyper-spectral images acquired by passive satellite sensors and Synthetic Aperture Radar (SAR) images acquired from active systems for Earth Observation. Copernicus data acquired by the new ESA Sentinels will be considered. The goal is to design novel methods able to use temporal correlation to model landcover behaviors, changes and trends for a better understanding of phenomena over the past and the future for a better modeling and understanding of climate change. Besides the requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
- master degree in Electrical Engineering, Communication Engineering, Computer Science, Mathematics or equivalents;
- knowledge in pattern recognition, deep learning, image/signal processing, statistic/remote sensing, passive/active sensors.
Contact: Francesca Bovolo bovolo [at] fbk.eu
D3 - Learning-based 3D scene understanding (1 grant)
3D scene understanding using learning-based approaches is becoming largely employed in several application sectors including industry, automotive, surveillance and cultural heritage. Computational algorithms that are traditionally used to process 2D images, such as object detection, tracking and segmentation, are nowadays being successfully extended to process 3D data (e.g. point clouds). However, traditional 3D approaches rarely use the image content directly for their task, but often rely on mid-level representations (e.g. voxels, sparse point clouds) that disregard the rich context provided by images. Moreover, the availability of 3D data is limited because the effort for annotationing it is greater than its 2D counterpart. The goal of this PhD position is to advance the state of the art about 3D scene understanding by focusing on the aspects of learning-based approaches that can potentially leverage different sensor modalities and the lack of human-annotated data.
Contact: Fabio Poiesi poiesi [at] fbk.eu