We consider the problem of recognizing an object from its silhouette. We focus on the case in which the camera translates, and rotates about a known axis parallel to the image, suc...
— This paper describes a robotic system that learns visual models of symmetric objects autonomously. Our robot learns by physically interacting with an object using its end effec...
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
There are three basic segmentation schemes for compound image compression: object-based, layer-based, and block-based. This work discusses the relative advantages of each scheme a...
This paper introduces a video object segmentation algorithm developed in the context of the European project Art.live1 where constraints on the quality of segmentation and the pro...
Alice Caplier, Laurent Bonnaud, Jean-Marc Chassery