— This paper introduces a product quantization based approach for approximate nearest neighbor search. The idea is to decomposes the space into a Cartesian product of low dimensi...
Searching for non-text data (e.g., images) is mostly done by means of metadata annotations or by extracting the text close to the data. However, supporting real content-based audi...
In this paper, we propose a novel method for fast nearest neighbors retrieval in non-Euclidean and non-metric spaces. We organize the data into a hierarchical fashion that preserv...