Appropriate datasets are required at all stages of object recognition research, including learning visual models of object and scene categories, detecting and localizing instances ...
Jean Ponce, Tamara L. Berg, Mark Everingham, David...
We describe an approach for extracting threedimensional articulated motion from unrestricted monocular video sequences. We combine feature extraction methods based on active conto...
Jane Wilhelms, Allen Van Gelder, L. Atkinson-Derma...
This work is about the integration of the skills robot control, landmark recognition, and qualitative reasoning in a single autonomous mobile system. It deals with the transfer of ...
W e quantify the observation by Kender and Freudenstein [6] that degenerate views occupy a significant fraction of the viewing sphere surrounding an object. This demonstrates that...
We propose a novel method to estimate the object that a user is focusing on by using the synchronization between the movements of objects and a user's eyes as a cue. We first ...