79 search results - page 5 / 16 » Robust Object Tracking with Online Multiple Instance Learnin... |
ECCV
2010
Springer
13 years 9 months ago
2010
Springer
We propose a novel system for associating multi-target tracks across multiple non-overlapping cameras by an on-line learned discriminative appearance affinity model. Collecting rel...
CVPR
2010
IEEE
14 years 2 days ago
2010
IEEE
Learning the knowledge of scene structure and tracking a large number of targets are both active topics of computer vision in recent years, which plays a crucial role in surveilla...
PAMI
2008
13 years 7 months ago
2008
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 po...
CVPR
2011
IEEE
13 years 4 months ago
2011
IEEE
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
CVPR
2010
IEEE
13 years 12 months ago
2010
IEEE
The design of robust classifiers, which can contend with the noisy and outlier ridden datasets typical of computer vision, is studied. It is argued that such robustness requires l...