Typical content-based image retrieval (CBIR) solutions with regular Euclidean metric usually cannot achieve satisfactory performance due to the semantic gap challenge. Hence, rele...
Given a query image of an object, our objective is to retrieve all instances of that object in a large (1M+) image database. We adopt the bag-of-visual-words architecture which ha...
Ondrej Chum, James Philbin, Josef Sivic, Michael I...
The primary business model behind Web search is based on textual advertising, where contextually relevant ads are displayed alongside search results. We address the problem of sel...
Filip Radlinski, Andrei Z. Broder, Peter Ciccolo, ...
The authors developed an extensible system for video exploitation that puts the user in control to better accommodate novel situations and source material. Visually dense displays...
Ming-yu Chen, Michael G. Christel, Alexander G. Ha...
This paper presents a novel approach for automatic person labelling in video sequences using costumes. The person recognition is carried out by extracting the costumes of all the p...