We address the problem of fusing sparse and noisy depth data obtained from a range finder with features obtained from intensity images to estimate ego-motion and refine 3D struct...
The acquisition of human motion data is of major importance for creating interactive virtual environments, intelligent user interfaces, and realistic computer animations. Today’...
Christian Theobalt, Marcus A. Magnor, Pascal Sch&u...
A motion-based side-information generation scheme with semi super-resolution for a scalable Wyner-Ziv coder framework is introduced. It is known that the performance of any Wyner-...
Bruno Macchiavello, Ricardo L. de Queiroz, Debargh...
The large shape variability and partial occlusions challenge most object detection and tracking methods for nonrigid targets such as pedestrians. Single camera tracking is limited...
Manas Kamal Bhuyan, Brian C. Lovell, Abbas Bigdeli
The INESC Porto group has participated in the search task (automatic and interactive). Our approach combines high-level features (the 39 concepts of the LSCOM-Lite set) with low-l...
Catalin Calistru, Cristina Ribeiro, Gabriel David,...