In interest point based human action recognition, local descriptors are used to represent information in the neighbourhood around each extracted space-time interest point. The per...
This paper presents a novel classification strategy for 3D objects. Our technique is based on using a Global Geodesic Function to intrinsically describe the surface ofan object. T...
A new combinatorial characterization of a gray-tone image called Euler Vector is proposed. Euler number of a binary image is a well-known topological feature, which remains invari...
Arijit Bishnu, Bhargab B. Bhattacharya, Malay Kuma...
The rich collection of successes in property testing raises a natural question: Why are so many different properties turning out to be locally testable? Are there some broad "...
Arnab Bhattacharyya, Victor Chen, Madhu Sudan, Nin...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...