Indexing echocardiogram videos at different levels of structure is essential for providing efficient access to their content for browsing and retrieval purposes. We present a nove...
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
?We present a method to automatically localize captions in JPEG compressed images and the I-frames of MPEG compressed videos. Caption text regions are segmented from background ima...
We introduce a novel framework for automatic 3D facial expression analysis in videos. The preliminary results were demonstrated by editing the facial expression with facial recogni...
Ya Chang, Marcelo Bernardes Vieira, Matthew Turk, ...
In this paper, we present a new representation of sports stract — Music Sports-Video (MSV), which provides exciting sports content accompanied with high quality background music...