51 search results - page 2 / 11 » Knowledge-Based Supervised Learning Methods in a Classical P... |
ICRA
2010
IEEE
13 years 3 months ago
2010
IEEE
— Detecting the boundaries of objects is a key step in separating foreground objects from the background, which is useful for robotics and computer vision applications, such as o...
CVPR
2010
IEEE
14 years 20 days ago
2010
IEEE
A recent dominating trend in tracking called tracking-by-detection uses on-line classifiers in order to redetect objects over succeeding frames. Although these methods usually deli...
Publication
Providing methods to support semantic interaction with growing volumes of video data is an increasingly important challenge for data mining. To this end, there has been some succes...
EMMCVPR
2007
Springer
13 years 11 months ago
2007
Springer
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
ICCV
2005
IEEE
13 years 10 months ago
2005
IEEE
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...