Image matching has been a central research topic in computer vision over the last decades. Typical approaches to correspondence involve matching features between images. In this pa...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
The web contains lots of interesting factual information about entities, such as celebrities, movies or products. This paper describes a robust bootstrapping approach to corrobora...
We present a new approach to semi-supervised anomaly detection. Given a set of training examples believed to come from the same distribution or class, the task is to learn a model ...
—Web-scale image search engines (e.g. Google Image Search, Bing Image Search) mostly rely on surrounding text features. It is difficult for them to interpret users’ search int...
Xiaoou Tang, Ke Liu, Jingyu Cui, Fang Wen, Xiaogan...