The first part of this talk considers a family of metrics to compare images based on their local descriptors. It encompasses the VLAD descriptor and matching techniques such as Hamming embedding. Making the bridge between these approaches yields a match kernel that takes the best of existing techniques by combining an aggregation procedure with a selective match kernel.

Since image search using either local or global descriptors boils down to approximate nearest neighbor search, the second part of this talk considers this problem, focusing on vector quantization methods. A recent method is presented whereby residuals over a coarse quantizer are used to locally optimize an individual product quantizer per cell. Non-exhaustive search strategies are discussed, including an inverted multi-index.

Yannis Avrithis, invited talk at µ-Workshop on Computer Vision, INRIA Rennes, 2 October 2014 [Slides]