We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
Nowadays numerous social images have been emerging on the Web. How to precisely label these images is critical to image retrieval. However, traditional image-level tagging methods...
Yang Yang, Yi Yang, Zi Huang, Heng Tao Shen, Feipi...
The PDF format is commonly used for the exchange of documents on the Web and there is a growing need to understand and extract or repurpose data held in PDF documents. Many system...
Abstract. We present a novel template matching framework for detecting geometrically transformed objects. A template is a simplified representation of the object of interest by a s...
This paper presents novel text input methods for mobile devices. In particular, it shows how users can capture text from books, newspapers, and other objects by using the digital ...