Learning to traverse image manifolds
Research output: Contribution to journal › Conference article › Research › peer-review
We present a new algorithm, Locally Smooth Manifold Learning (LSML), that learns a warping function from a point on an manifold to its neighbors. Important characteristics of LSML include the ability to recover the structure of the manifold in sparsely populated regions and beyond the support of the provided data. Applications of our proposed technique include embedding with a natural out-of-sample extension and tasks such as tangent distance estimation, frame rate up-conversion, video compression and motion transfer.
Original language | English |
---|---|
Journal | Advances in Neural Information Processing Systems |
Pages (from-to) | 361-368 |
Number of pages | 8 |
ISSN | 1049-5258 |
Publication status | Published - 2007 |
Externally published | Yes |
Event | 20th Annual Conference on Neural Information Processing Systems, NIPS 2006 - Vancouver, BC, Canada Duration: 4 Dec 2006 → 7 Dec 2006 |
Conference
Conference | 20th Annual Conference on Neural Information Processing Systems, NIPS 2006 |
---|---|
Country | Canada |
City | Vancouver, BC |
Period | 04/12/2006 → 07/12/2006 |
ID: 302051790