Publications

Figure from: Towards inferring cognitive state changes from pupil size variations in real world conditions

Towards inferring cognitive state changes from pupil size variations in real world conditions

Eye Tracking Research and Applications (ETRA)· 2020

N. V. Kartheek Medathati, Ruta Desai, James Hillis

In this paper we study how far we are from estimating cognitive state changes from eye movements in real world environments using a variety of visual search tasks

Figure from: Recurrent network dynamics reconciles visual motion segmentation and integration.

Recurrent network dynamics reconciles visual motion segmentation and integration.

Scientific Reports· 2017

N. V. K. Medathati, J. Rankin, A. I. Meso, P. Kornprobst, G. S. Masson

This paper characterizes the complex spatio-temporal dynamics of MT neurons

Figure from: Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

Computer Vision and Image Understanding· 2016

N. V. Kartheek Medathati, Heiko Neumann, Guillaume S. Masson, Pierre Kornprobst

A review paper exploring the mutual benefits of biological and computer vision — how methods used to understand the visual cortex can make machine vision more robust.

Figure from: What can we expect from a V1-MT feedforward architecture for optical flow estimation?

What can we expect from a V1-MT feedforward architecture for optical flow estimation?

Signal Processing: Image Communication· 2015

Fabio Solari, Manuela Chessa, N. V. Kartheek Medathati, Pierre Kornprobst

We show how a V1-MT neural model can be adapted to handle real sequences.

Figure from: Decoding MT motion response for optical flow estimation: An experimental evaluation

Decoding MT motion response for optical flow estimation: An experimental evaluation

European Signal Processing Conference (EUSIPCO)· 2015

M. Chessa, N. V. Kartheek Medathati, G. S. Masson, F. Solari, P. Kornprobst

Decoding the motion energies is of natural interest for developing biologically inspired computer vision algorithms for dense optical flow estimation. Here, we address this problem by evaluating four strategies for motion decoding: intersection of constraints, linear decoding through learned weights on MT responses, maximum likelihood and regression with neural network using multi scale-features.

Figure from: Detection and discrimination of disease-related abnormalities based on learning normal cases

Detection and discrimination of disease-related abnormalities based on learning normal cases

Pattern Recognition· 2012

K. Sai Deepak, N. V. Kartheek Medathati, Jayanthi Sivaswamy

In this paper, we observe the key challenges for representation and feature extraction schemes to be met for detection of abnormalities by learning normal cases.

Figure from: Local descriptor based on texture of projections

Local descriptor based on texture of projections

Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP)· 2010

N. V. Kartheek Medathati, Jayanthi Sivaswamy

In this paper we propose a novel descriptor that better captures shape information by analysing texture of the radon transform

Figure from: Robust matching of multi-modal retinal images using radon transform based local descriptor

Robust matching of multi-modal retinal images using radon transform based local descriptor

ACM International Health Informatics Symposium (IHI)· 2010

Yogesh Babu Bathina, N. V. Kartheek Medathati, Jayanthi Sivaswamy

A novel Radon Transform based descriptor is proposed, which is invariant to illumination, rotation and partially to scale.

Figure from: Synthetic zooming of tomographic images by combination of lattices

Synthetic zooming of tomographic images by combination of lattices

IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)· 2010

N. Dixit, N. V. Kartheek Medathati, J. Sivaswamy

We propose a method for synthetic zooming of tomographic images by applying super resolution technique on reconstructed data via a union of rotated lattices.