We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this a...
Yuanhao Chen, Long Zhu, Alan L. Yuille, HongJiang ...
It is possible to broadly characterize two approaches to probabilistic modeling in terms of generative and discriminative methods. Provided with sufficient training data the discr...
With the rise of photo-sharing websites such as Facebook and Flickr has come dramatic growth in the number of photographs online. Recent research in object recognition has used su...
Yunpeng Li, David J. Crandall, Daniel P. Huttenloc...
This paper shows how semantic attribute features can be used to improve object classification performance. The semantic attributes used fall into five groups: scene (e.g. `road...
The selection of weak classifiers is critical to the success of boosting techniques. Poor weak classifiers do not perform better than random guess, thus cannot help decrease the t...