We present a statistical model for organizing image collections which integrates semantic information provided by associated text and visual information provided by image features...
Today's Content-Based Image Retrieval (CBIR) techniques are based on the "k-nearest neighbors" (kNN) model. They retrieve images from a single neighborhood using lo...
The analysis of the leading social video sharing platform YouTube reveals a high amount of redundancy, in the form of videos with overlapping or duplicated content. In this paper,...
Semantic analysis of multimodal video aims to index segments of interest at a conceptual level. In reaching this goal, it requires an analysis of several information streams. At s...
Cees Snoek, Marcel Worring, Arnold W. M. Smeulders
Learning the user’s semantics for CBIR involves two different sources of information: the similarity relations entailed by the content-based features, and the relevance relatio...