—It has been shown that the Universum data, which do not belong to either class of the classification problem of interest, may contain useful prior domain knowledge for training...
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm. The res...
Jianfeng Gao, Qiang Wu, Chris Burges, Krysta Marie...
We present SpeedBoost, a natural extension of functional gradient descent, for learning anytime predictors, which automatically trade computation time for predictive accuracy by s...
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...