Since the emergence of extensive multimedia data, feature fusion has been more and more important for image and video retrieval, indexing and annotation. Existing feature fusion t...
Yun Fu, Liangliang Cao, Guodong Guo, Thomas S. Hua...
There are well-established methods for reducing the number of support vectors in a trained binary support vector machine, often with minimal impact on accuracy. We show how reduce...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...