Recent advances in multimedia technologies lead to a massive storage of multimedia data, which in turn urges us to create the metadata about the data for facilitating a sophisticated search based on their contents among the huge multimedia database. Among these data, video is the most challenging one because of their large size and highly unstructured nature. This paper presents an approach for video annotation based on human perception by annotating the key objects present in the video using the technique combining Bottom up- Saliency based region selection and SIFT.
cited By (since 1996)0; Conference of org.apache.xalan.xsltc.dom.DOMAdapter@540ba479 ; Conference Date: org.apache.xalan.xsltc.dom.DOMAdapter@485b2f0a Through org.apache.xalan.xsltc.dom.DOMAdapter@5a6d5ea2
Ja Amudha, Soman, K. Pb, and Vasanth, Kc, “Video annotation using saliency”, in Proceedings of the 2008 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2008, Las Vegas, NV, 2008, pp. 191-195.