We introduce a new framework for the automatic selection of the best views of 3D models. The approach is based on the assumption that models belonging to the same class of shapes ...
—Machine learning is inherently a multiobjective task. Traditionally, however, either only one of the objectives is adopted as the cost function or multiple objectives are aggreg...
Recently, the bag-of-words (BOW) based image representation is getting popular in object categorization. However, there is no available visual vocabulary and it has to be learned. ...
Chunjie Zhang, Jing Liu, Yi Ouyang, Hanqing Lu, So...
Abstract. A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especia...
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...