61 search results - page 9 / 13 » ijcv 2008 |
IJCV
2008
13 years 9 months ago
2008
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
IJCV
2008
13 years 9 months ago
2008
Abstract We propose a novel and efficient surface matching approach for reassembling broken solids as well as for matching assembly components using cluster trees of oriented point...
IJCV
2008
13 years 9 months ago
2008
This work achieves an efficient acquisition of scenes and their depths along long streets. A camera is mounted on a vehicle moving along a straight or a mildly curved path and a sa...
IJCV
2008
13 years 9 months ago
2008
Abstract We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our ...
IJCV
2008
13 years 9 months ago
2008
We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches be...