10615 search results - page 1831 / 2123 » Dynamic topic models |
152
click to vote
ICCV
2005
IEEE
16 years 6 months ago
2005
IEEE
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...
165
click to vote
ECCV
2008
Springer
16 years 6 months ago
2008
Springer
Abstract. Movies and TV are a rich source of diverse and complex video of people, objects, actions and locales "in the wild". Harvesting automatically labeled sequences o...
144
click to vote
ECCV
2002
Springer
16 years 6 months ago
2002
Springer
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
156
click to vote
ICIP
2008
IEEE
16 years 6 months ago
2008
IEEE
We consider the problem of reconstructing time sequences of spatially sparse signals (with unknown and time-varying sparsity patterns) from a limited number of linear "incohe...
158
click to vote
ICIP
2008
IEEE
16 years 6 months ago
2008
IEEE
Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summar...