TY - GEN

T1 - Learning to traverse image manifolds

AU - Dollár, Piotr

AU - Rabaud, Vincent

AU - Belongie, Serge

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=67349259478&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:67349259478

SP - 361

EP - 368

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

T2 - 20th Annual Conference on Neural Information Processing Systems, NIPS 2006

Y2 - 4 December 2006 through 7 December 2006

ER -