This paper presents a fast and robust sprite generation algorithm for MPEG-4 video coding. Our contributions consist of two aspects. Firstly, a fast and robust Global Motion Estima...
We address the need for robust detection of obstructed human features in complex environments, with a focus on intelligent surgical UIs. In our setup, real-time detection is used t...
Data imputation approaches for robust automatic speech recognition reconstruct noise corrupted spectral information by exploiting prior knowledge of the relationship between targe...
—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
Representing and reasoning about time dependent information is a key research issue in many areas of computer science and artificial intelligence. One of the best known and widely...