ESTEVE VALLS MASCARÓ
Born in Spain, Esteve currently working in TUM as a PhD researcher on Human intention recognition and prediction for human robot collaborative behaviours. His main research interests are Computer Vision, Deep Learning and Action Understanding and prediction with the aim of understanding the human "Common Sense".
Esteve studied both the Telecommunications Engineering Degree and the Master in Advanced Telecommunications Technologies in UPC (Catalonia) with Computer Science as my main focus. He had the opportunity to also work in several companies while studying.
His background can be summarized in: Training Neural Networks for Object Detection and Image Classification. . Project management. Optimization and automatization of server processes. Design and Development of Android Applications. Cybersecurity Operator.
Esteve has already researched in the optimization of several deep learning architectures to speed up the computing time and to reduce the weight of the models without reducing the effectiveness of the tasks, as can be seen in my Master's Thesis: Multitask Networks for Micromobility Vision Applications. His work was to develop a system able to improve the safety of micro-vehicles' drivers and to perform several tasks on real time, ensuring the possiblity to deploy the system to a small device (as smartphone): detecting possible hazards on the road, to be aware of the environment tracking their position over time, to compute relative velocities classifying the type of road on which the vehicle circulates, to infer in the vehicle speed depending on the regulation applied to each type of road (i.e. in sidewalks the microvehicles can be driven).
Prof. Dongheui Lee