We introduce new techniques for extracting, analyzing, and visualizing textual contents from instructional videos of low production quality. Using Automatic Speech Recognition, ap...
In video surveillance, the sizes of face images are very small. However, few works have been done to investigate scalerobust face recognition. Our experiments on appearancebased m...
This is a high level computer vision paper, which employs concepts from Natural Language Understanding in solving the video retrieval problem. Our main contribution is the utiliza...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such ...
There are several approaches for pen-based systems to improve legibility of handwritten text, e.g. smoothing the strokes composing the characters and words. A very challenging sol...