About Me

I am a PhD student working under the supervision of Dr. Pierre Kornprobst and Dr. Guillaume Masson at BioVision team, INRIA Sophia Antipolis. My research interest lies at the intersection of computer vision, visual neuroscience and machine learning. I believe that recent advances in neurosciences can give us novel insights into developing robust vision/AI systems.

Currently, I am working on the problem of motion/optical flow estimation by scaling up the models rooted in physiology for application to naturalistic scenarios. At the same time I also use bifurcation theory and dynamical systems approach to characterize the motion estimation strategies in the primates.

Current research

  • N. V. K. Medathati, A. I. Messo, Guillaume S. Masson, Pierre Kornprobst and James Rankin, Understanding the impact of recurrent interactions on population tuning
    Poster at AREADNE 2016, Santorini, Greece
    (abstract [#88], poster)
  • N. V. K. Medathati, J. Rankin, G. S. Masson and P. Kornprobst, Exploring the Richness of Center-surround Dynamics: A Bifurcation Study
    Poster at Bardfest 2014: Nonlinear dynamics and stochastic methods: from neuroscience to other biological applications, Pittsburgh, USA
    (abstract [#18], poster)

Journal publications

  • N. V. K. Medathati, H. Neumann, G.S. Masson, P. Kornprobst, Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision, Computer Vision and Image Understanding (CVIU), Vol. 150, September, 2016
  • F. Solari, M. Chessa, N. V. K. Medathati and P. Kornprobst, What can we expect from a classical V1-MT feedforward architecture for optical flow estimation? ,
    Signal Processing: Image Communication, Vol. 39, Part B, pp. 342--354, 2015 (fulltext, Code@Modeldb , Special Thanks to Fabio and Manuella)
  • K. S. Deepak, N. V. K. Medathati and J. Sivaswamy, Detection and discrimination of disease related abnormalities based on learning normal cases,
    Journal of Pattern Recognition, Vol. 45, No. 10, pp. 3707--3716, 2012

Refereed Conference proceedings

  • N. V. K. Medathati, M. Chess, G. S. Masson, F. Solari, P. Kornprobst, Decoding MT motion representation for optical flow estimation: an experimental evaluation, EUSIPCO, Nice, France, 2015
  • N. V. K. Medathati and J. Sivaswamy, Local descriptor based on texture of projections , Proc. of 7th Indian Conference on Computer Vision, Graphics and Image Processing,, Chennai, India, 2010
  • B. Y. Babu, N. V. K. Medathati and J. Sivaswamy, Robust matching of multi-modal retinal images using radon transform based local descriptors, Proc. of 1st ACM International Health Informatics Symposium, New York, USA, 2010
  • N. Dixit, N.V. Kartheek Medathati and J. Sivaswamy, Synthetic zooming of tomographic images by combination of lattices, Proc. of Nuclear Science Symposium (NSS/MIC), Orlando, USA, 2009

Posters with abstract submission

  • N. V. K. Medathati, M. Chessa, G. S. Masson, P. Kornprobst, F. Solari, Adaptive Motion Pooling and Diffusion for Optical Flow
    Talk presented at Modvis workshop at VSS, Florida, USA, 2015 (abstract)
  • F. Solari, M. Chessa, N. V. K. Medathati and P. Kornprobst, Benchmarking biologically inspired spatio-temporal filter based optical flow estimation on modern datasets ,
    ViiHM: EPSRC network for biological and computer vision, Stratford-Upon-Avon, UK, 2014 (poster)
  • C. Hilario, N. V. K. Medathati, P. Kornprobst, V. Murino and D. Sona, A retina inspired descriptor for image classification ,
    ViiHM: EPSRC network for biological and computer vision, Stratford-Upon-Avon, UK, 2014 (poster)
  • N. V. Kartheek Medathati, J. Rankin, P. Kornprobst and G. S. Masson, A Retinotopic neural fields model of perceptual switching in 2D motion integration ,
    Bernstein Conference, Tuebingen, Germany, 2013 (poster)

Attended Summer Schools

  • The Computational Vision Summer School
    Location: Freudenstadt-Lauterbad, Black Forest, Germany
    This is unique summer school offering a broad perspective on biological vision with lectures focussed on theoretical and computation aspects involved.
    Program chairs: Matthias Bethge, Michael Black, Roland Fleming, Felix Wichmann
    See the program and invited speaker list CVSS

  • ENS/INRIA Visual Recognition and Machine Learning Summer School
    Location: Ecole Normale Superiéure campus, Paris, France
    The program provides an intense description of the visual recognition together with the related machine learning algorithms.
    Organizers Zaid Harchaoui, Ivan Laptev, Jean Ponce, Cordelia Schmid, Josef Sivic See the program and lectures CVML