Latent Semantic Analysis (LSA) has shown encouraging performance for the problem of unsupervised image automatic annotation. LSA conducts annotation by keywords propagation on a l...
Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summar...
In this paper we are interested in describing Web pages by how users interact within their contents. Thus, an alternate but complementary way of labelling and classifying Web docu...
We propose a system that registers and retrieves text documents to annotate them on-line. The user registers a text document captured from a nearly top view and adds virtual annot...
We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...