This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAM)-based approaches have achieved some success, t...
We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying featur...
Pei Yin, Irfan A. Essa, Thad Starner, James M. Reh...
—A novel feed-forward pulse width modulation (FF-PWM) technique is proposed for improving line regulation of buck or boost (BOB) converters. In order to provide a regulated suppl...
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 additiona...
Abstract—Integrated power supplies are critical building blocks in stateof-the-art portable applications, where they efficiently and accurately transform a battery supply into va...