This paper exploits the context of natural dynamic scenes
for human action recognition in video. Human actions
are frequently constrained by the purpose and the physical
propert...
Marcin Marszalek (INRIA), Ivan Laptev (INRIA), Cor...
A general framework simultaneously addressing pose
estimation, 2D segmentation, object recognition, and 3D
reconstruction from a single image is introduced in this
paper. The pr...
Relief mosaics are collections of registered images that extend traditional mosaics by supporting motion parallax. A simple parallax interpolation algorithm based on computed corr...
Maxime Lhuillier, Long Quan, Harry Shum, Hung-Tat ...
Speech reading, also known as lip reading, is aimed at extracting visual cues of lip and facial movements to aid in recognition of speech. The main hurdle for speech reading is th...
Configurations of dense locally parallel 3D curves occur in medical imaging, computer vision and graphics. Examples include white matter fibre tracts, textures, fur and hair. We d...