Cheng Lei

Shape Time Discriminative Classification of Video Objects (2008)

Li Cheng, Baochun Bai, Cheng Lei, Dale Schuurmans, Shaojun Wang

We propose a discriminative approach to non-rigid video objects classification. Our goal is to recognize actions of the objects that appear in a video sequence, based on its shape time dynamics. This...

Real-time Backward Disparity-based Rendering for Dynamic Scenes using Programmable Graphics Hardware (2008)

Minglun Gong, Jason M. Selzer, Cheng Lei, Yee-hong Yang

Figure 1: Novel views synthesized using different approaches. Since the scene is sparsely sampled using 16 images, the color interpolation-based approach only keeps part of the scene (background...