Interactive video technology is meant to support user-interaction with video in scene objects associated with navigation in video segments and access to text-based metadata. Inter...
Rudinei Goularte, Edson dos Santos Moreira, Maria ...
We introduce an approach for physically-grounded natural language interpretation by robots which reacts appropriately to unanticipated physical changes in the environment and dyna...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
In this paper, we propose an e cient technique for the animation of exible thin objects. Massspring model was employed to represent the exible objects. Many techniques have used t...
Recent progress in per-pixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Wit...