We consider the design of an image representation that embeds and aggregates a set of
local descriptors into a single vector. Popular representations of this kind include the bag-of …

Most image encodings achieve orientation invariance by aligning the patches to their
dominant orientations and translation invariance by completely ignoring patch position or by …

Recent years have witnessed a number of studies on distance metric learning to improve
visual similarity search in content-based image retrieval (CBIR). Despite their successes …

We consider the design of a single vector representation for an image that embeds and
aggregates a set of local patch descriptors such as SIFT. More specifically we aim to …

This paper considers a family of metrics to compare images based on their local descriptors.
It encompasses the VLAD descriptor and matching techniques such as Hamming …

This paper introduces recent methods for large scale image search. State-of-the-art methods
build on the bag-of-features image representation. We first analyze bag-of-features in the …

Content-based image retrieval using region segmentation has been an active research
area. We present IRM (Integrated Region Matching), a novel similarity measure for region …

Small set with the default threshold, large set with lower threshold. Number of features
indexed without (SMK-SMK⋆) and with (ASMK− ASMK⋆) aggregation are reported …

In visual recognition, the images are frequently modeled as sets of local features (bags). We
show that bag of words, a common method to handle such cases, can be viewed as a …

In the last few years, large-scale image retrieval has attracted a lot of attention from the
multimedia community. Usual approaches addressing this task first generate an initial …