This paper proposes systematic lossy error protection of video waveforms using multiple embedded Wyner-Ziv video descriptions. A video signal transmitted over an error-prone chann...
We propose the "ninja cursor" to improve the performance of target acquisition, particularly on large screens. This technique uses multiple distributed cursors to reduce...
Abstract— This paper presents an Interleaver-Division Multiple Access (IDMA) based architecture with single-user decoding using parallel concatenated non-linear trellis codes (PC...
Miguel Griot, Andres I. Vila Casado, Richard D. We...
Abstract. Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture...
Pattern recognition and computer vision tasks are computationally intensive, repetitive, and often exceed the capabilities of the CPU, leaving little time for higher level tasks. ...