This paper presents an approach for including 3D prior models into a factorization framework for structure from motion. The proposed method computes a closed-form affine fit which...
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
A single face classifier has difficulty in detecting multiview faces under real and complex scenes due to various poses, cluttering environment and small size of faces. In this pa...
Low-level image processing algorithms generally provide noisy features that are far from being Gaussian. Medium-level tasks such as object detection must therefore be robust to out...
Sio-Song Ieng, Jean-Philippe Tarel, Pierre Charbon...