258 search results - page 16 / 52 » Using Co-Occurrence and Segmentation to Learn Feature-Based ... |
157
click to vote
ECCV
2008
Springer
16 years 4 months ago
2008
Springer
Abstract. The visual analysis of human manipulation actions is of interest for e.g. human-robot interaction applications where a robot learns how to perform a task by watching a hu...
146
Voted
UAI
2004
15 years 4 months ago
2004
We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to d...
247
Voted
IWINAC
2011
Springer
14 years 5 months ago
2011
Springer
Abstract. One of the more important issues in intelligent video surveillance systems is the ability to handle events from the motion of objects. Thus, the classification of the tr...
155
Voted
ICMCS
2008
IEEE
15 years 9 months ago
2008
IEEE
Several stochastic models provide an effective framework to identify the temporal structure of audiovisual data. Most of them need as input a first video structure, i.e. connecti...
139
Voted
WWW
2004
ACM
16 years 3 months ago
2004
ACM
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...