Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn m...
Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. “person”, “dog”, “chair”, etc.) and their visual attributes (e.g....
In video object classification, insufficient labeled data may at times be easily augmented with pairwise constraints on sample points, i.e, whether they are in the same class or n...
Rong Yan, Jian Zhang, Jie Yang, Alexander G. Haupt...
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...