Most motion-based tracking algorithms assume that objects undergo rigid motion, which is most likely disobeyed in real world. In this paper, we present a novel motion-based tracking framework which makes no such assumptions. Object is represented by

The 3-D Morphable Model was introduced as a generative model to p redictthe appearances o f an individual while using a statistical prior on shape and texture allowin g its parameters to be estimated from single image. Based on these new unde

这是一篇关于多个物体类的协同分割应用到视频分割的论文。-Multi-Class Video Co-Segmentation with a Generative Multi-Video Model ；2013 IEEE Conference on Computer Vision and Pattern Recognition

A Generative Model for the Joint Registration of Multiple Point Sets