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...
In this paper, we propose an object detection approach using spatial histogram features. As spatial histograms consist of marginal distributions of an image over local patches, th...
In this paper, we propose a novel personalized ranking system for amateur photographs. Although some of the features used in our system are similar to previous work, new features,...
Che-Hua Yeh, Yuan-Chen Ho, Brian A. Barsky, Ming O...
This paper presents a fully automatic framework for the restoration of double-sided historical manuscripts which are impaired by ink bleed-through distortions. First, the recto si...
We address the challenge of semantic gap reduction for image retrieval through an improved SVM-based active relevance feedback framework, together with a hybrid visual and concept...