For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness ...
Liwei Wang, Yin Li, Jiaya Jia, Jian Sun, David Wip...
We present a family of incremental Perceptron-like algorithms (PLAs) with margin in which both the "effective" learning rate, defined as the ratio of the learning rate t...
—We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of insta...
Whenever a class is invited to ask questions, it is individual learners who ask and their questions do not often represent the questions of the whole class. The benefit to those p...
Finding a point which minimizes the maximal distortion with respect to a dataset is an important estimation problem that has recently received growing attentions in machine learnin...