This work presents a browser that supports two strategiesfor video browsing: the navigation through visual hierarchies and theretrieval of similar images and objects. The input videos are rstly pro-cessed by a keyframe extractor to reduce the temporal redundancy anddecrease the number of elements to consider. These generated keyframesare hierarchically clustered with the Hierachical Cellular Tree (HCT)algorithm, an indexing technique that also allows the creation of datastructures suitable for browsing. Di erent clustering criteria are avail-able, in the current implementation, based on four MPEG-7 visual de-scriptors computed at the global scale. The navigation can directly drivethe user to nd the video timestamps that best match the query or to akeyframe which is globally or locally similar in visual terms to the query.If this is the case, a visual search engine is also available to nd othersimilar keyframes or regions, also based on MPEG-7 visual descriptors.

The original publication is available at www.springerlink.com