In this work, we present an automatic child gesture recognition system, which has wide application in child language analysis and other areas in Cognitive Science communities.

In this work, we present a human pose tracking method with a new part descriptor. We formulate the human pose tracking problem as a discrete optimization problem based on spatio-temporal pictorial structure model and solve this problem in dynamic programming framework very efficiently.

In this work we present a novel Space Time Interest Point detection (STIP) method based on 3D facet model, we call it as FaSTIP. Also we propose a new point descriptor based on 3D wavelet transform.

In this project we consider a cultural activity classification problem, namely classification of Indian Classical Dance (ICD). To best of our knowledge this is a novel application of computer vision.

Fundus retinal image has many parts (fovea region, blood vessels etc.), those are extremly important to diagnosis different eye diseases. Here we proposed an algorithm to efficiently detect the fovea region in fundus retinal image.