:: About Me

Brego

I am a Ph.D. student in the Computer Science Department, Vision group at Queen Mary University of London. I am working for BEWARE project and my supervisors are Tao Xiang and Shaogang Gong.

I received my Bachelor of Science from Politecnico di Milano (Italy). During my Bachelor I had the opportunity to attend Ecole Centrale Marseille as an exchange student for one semester. In 2006, I received my Master of Science in Telecommunication Engineering from Politecnico di Milano (Italy), where I specialized in signal processing and networks. As part of my master’s degree, I was a guest research student at Queen Mary University of London's Multimedia and Vision group, where I conducted research in audio visual tracking.

Immediately following my master’s degree, I worked as a research engineer in Milan for a year before starting my Ph.D. at Queen Mary, University of London in November of 2007.

My research interests include signal processing, computer vision, Bayesian models, statistics and machine learning. I am currently working on human actions modelling and recognition. My project’s purpose is to detect and recognize human actions from videos captured in unconstrained scenarios such as: CCTV cameras, YouTube clips, mobile phones videos and TV movies.

    :: Publications

    1) Multi-Modal Particle Filtering Tracking using Appearance, Motion and Audio Likelihoods.
    IEEE International Conference on Image Processing (ICIP) 2007, San Antonio, TX .
    [PDF]

    2) Recognising Action as Clouds of Space-Time Interest Points.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009, Miami, FL.
    [PDF] [VIDEO] [POSTER] [CODE IP] [CODE COP]

    3) Action Recognition with Cascaded Feature Selection and Classification.
    International Conference on Imaging for Crime Detection and Prevention (ICDP) 2009, London, UK.
    [PDF] [SLIDES]

    4) Discriminative Topics Modelling for Action Feature Selection and Recognition.
    British Machine Vision Conference (BMVC) 2010, Aberystwyth, UK.
    [PDF] [POSTER] [VIDEO] [CODE]

    5) Fusing Appearance and Distribution Information of Interest Points for Action Recognition.
    Pattern Recognition, Vol. 45, No. 3, pp. 1220-1234, March 2012.
    [PDF]

      :: Teaching Assistant

      Academic year: 2007-2008
        - Language and Communication (DCS103) 2nd Semester

      Academic year: 2008-2009
        - Computer Architecture (DCS111) 1st Semester
        - Further Networks and Operating Systems (DCS201) 2nd Semester

      Academic year: 2009-2010
        - Computer Architecture (DCS111) 1st Semester
        - Further Networks and Operating Systems (DCS201) 2nd Semester

      Academic year: 2010-2011
        - Computer Architecture (DCS111) 1st Semester
        - C++ for Image Processing (DCS339) 1st Semester

      :: Activities

      Organising Committee Member:
        - the 20th British Machine Vision Conference, London, UK, 2009
        - the 1th Annual EECS Postgraduate Conference, London, UK, 2009.
        - the 2nd Annual EECS Postgraduate Conference, London, UK, 2010.
        - the 2010 Electronic Engineering and Computer Science Research Open Day , London, UK, 2010.

      Member:
        - Student Member, the Institute of Electrical and Electronic Engineers (IEEE), since 2008.
        - British Machine Vision Association (BMVA), since 2010.

      :: Awards

      - Full EPSRC Scholarship, Queen Mary University of London, 2007-2010.
      - "Make it Happen" project from ESD, Queen Mary University of London, 2009.

      :: My Thesis

      - Representation and Recognition of Human Actions in Video, QMUL, London, 2011
      [PDF] [SLIDES] [TEMPLATE_LATEX]

      :: Contacts


      Address:
      Computer Science Department
      Queen Mary, University of London
      London, E1 4NS, UK.
      E-mail: bregonzio (at) gmail . com 
      Phone: +44(0) 207 882 8019
      Room: CS 329

      :: Demo

      CVPR 2009: Recognising Action as Clouds of Space-Time Interest Points:

      ICDP 2009: Action Recognition with Cascaded Feature Selection and Classification:

      BMVC 2010: Discriminative Topics Modelling for Action Feature Selection and Recognition: