We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human b...
Long Zhu, Yuanhao Chen, Yifei Lu, Chenxi Lin, Alan...
We have created the first image search engine based entirely on faces. Using simple text queries such as "smiling men with blond hair and mustaches," users can search thr...
Background: This paper introduces the notion of optimizing different norms in the dual problem of support vector machines with multiple kernels. The selection of norms yields diff...
In this paper we present a novel strategy, DragPushing, for improving the performance of text classifiers. The strategy is generic and takes advantage of training errors to succes...
Songbo Tan, Xueqi Cheng, Moustafa Ghanem, Bin Wang...
In this paper we unify two supposedly distinct tasks in multimedia retrieval. One task involves answering queries with a few examples. The other involves learning models for seman...