We present a novel approach for unsupervised discovery of repetitive objects from 3D point clouds. Our method assumes that objects are geometrically consistent, and uses multiple o...
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered sce...
My thesis aims to contribute towards building autonomous agents that are able to understand their surrounding environment through the use of both audio and visual information. To ...