Abstract. A tracking-by-detection framework is proposed that combines nearest-neighbor classification of bags of features, efficient subwindow search, and a novel feature selection...
Random Forests were introduced by Breiman for feature (variable) selection and improved predictions for decision tree models. The resulting model is often superior to AdaBoost and ...
Long Han, Mark J. Embrechts, Boleslaw K. Szymanski...
This paper presents a novel feature-matching based approach for rigid object tracking. The proposed method models the tracking problem as discovering the affine transforms of obje...
Weiyu Zhu, Song Wang, Ruei-Sung Lin, Stephen E. Le...
In the paper we present a generalized discriminative multiple instance learning algorithm (GD-MIL) for multimedia semantic concept detection. It combines the capability of the MIL...
Accurate image correspondence is crucial for estimating multiple-view geometry. In this paper, we present a registration-based method for improving accuracy of the image correspond...