PhD Program in Smart Computing
PhD program in Smart Computing at the Department of Information Engineering of the University of Florence http://smartcomputing.unifi.it/
Among the others, for the current PhD program starting in November 2017, we seek highly motivated students for the two following positions (deadline for applications to be defined, but between June to July 2017):

  • Human Movement Analysis
    Analysis of the movement of the human body is central in problems like human action recognition, human behavior understanding, human-object and human-human interaction, avatar animation, emotion detection, gait recognition, etc. A recent trend in this area is that of investigating such aspects using RGB-D sensors that jointly capture photometric and depth data (the body skeleton is typically also available from these data). Extracting representations of such dynamic sequences of RGB-D frames often results in descriptors with an underlying structure, which lay in a non-Euclidean space.
    In this PhD theme proposal, we aim to investigate methods for representing human movements in RGB-D sequences. In particular, we are interested in matrix manifold solutions that shown the potential to effectively manage the non-linearity of such data. In addition, such geometric data are large and complex, and are natural targets for machine learning techniques. In many applications, Deep neural networks have been recently proven to be powerful tools, but these tools have been most successful on data with an underlying Euclidean or grid-like structure, and in cases where the invariances of these structures are built into networks used to model them. We also aim to investigate emerging techniques attempting to generalize (structured) deep neural models to non-Euclidean domains such as graphs and manifolds.
    Ideal candidates should have or expect to obtain a MSc or equivalent degree in Computer Science, Mathematics, Physics or closely related disciplines. The following qualities are desirable: strong interests in one or more of the involved research areas (machine learning, computer vision, high performance computing); excellent record of academic and/or professional achievement; strong mathematical and programming skills; good written and spoken communication skills in Italian or English.
    Successful candidates will be supervised in Florence by Prof. Pietro Pala and Prof. Stefano Berretti, with potential for collaboration with the University of Lille. Applicants should get in touch as soon as possible with Prof. Pietro Pala and Prof. Stefano Berretti and will have to formally apply for a public competition by June / July 2017.
  • Online 3D Human Models Reconstruction from RGB-D Cameras for Recognition Applications
    Thanks to the introduction of low cost RGB-D cameras, generic still or dynamic scenes can be monitored for the extraction of depth and RGB data streams at video rates. Hence, traditional video-based approaches to the analysis of the observed scenes can be complemented with the analysis of 3D data representing the geometry of the scenes. However, 3D data acquired by such devices are usually of low-resolution, and can be not adequate for fine level analysis. In this theme proposal, we aim primarily at investigating how to exploit the temporal redundancy of depth data to reconstruct 3D face and body models, either static or dynamic, of the imaged subjects at a higher resolution. The ultimate goal is to enable the study and design of more effective and efficient solutions for person recognition, re-identification and activity understanding, also in active vision scenarios. Since the time efficiency is a crucial aspect for many of these applications, we will target solutions that take advantage of GPU computation.
    Ideal candidates should have or expect to obtain a MSc or equivalent degree in Computer Science, Mathematics, Physics or closely related disciplines. The following qualities are desirable: strong interests in one or more of the involved research areas (machine learning, computer vision, high performance computing); excellent record of academic and/or professional achievement; strong mathematical and programming skills; good written and spoken communication skills in Italian or English.
    Successful candidates will be supervised in Florence by Prof. Pietro Pala and Prof. Stefano Berretti. Applicants should get in touch as soon as possible with Prof. Pietro Pala and Prof. Stefano Berretti and will have to formally apply for a public competition by June / July 2017.


Call for papers: ACM TOMM Special Issue
The ACM Transactions on Multimedia Computing, Communications and Applications (ACM TOMM), will host the special issue on Representation, Analysis and Recognition of 3D Humans. More information on the SI can be found in the call at the following link: SI call for papers. Paper submission deadline June 15, 2017.

International Conferences
We will present one paper at the upcoming IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Biometrics, ICPR 2016, Honolulu, Hawaii, Usa, July 21-26, 2017


Past Events