We investigate the problem of learning the structure of an articulated object, i.e. its kinematic chain, from feature trajectories under affine projections. We demonstrate this po...
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
We present a higher-level visual representation, visual synset, for object categorization. The visual synset improves the traditional bag of words representation with better discr...
Yantao Zheng, Ming Zhao 0003, Shi-Yong Neo, Tat-Se...
Embedding generic shape information into probabilistic spatiotemporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuab...