Learning to Traverse Image Manifolds
Annual Conference on Neural Information Processing Systems(2006)
摘要
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. Appli- cations 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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络