The ERICA switch algorithm has been discussed extensively in TM group in the past. However, over the last two years, the algorithm has been substantially modified. This contributio...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
We present a new approach to robustly solve photometric stereo problems. We cast the problem of recovering surface normals from multiple lighting conditions as a problem of recover...
Background: Current approaches to parameter estimation are often inappropriate or inconvenient for the modelling of complex biological systems. For systems described by nonlinear ...
Neighborhood search heuristics like local search and its variants are some of the most popular approaches to solve discrete optimization problems of moderate to large size. Apart ...