English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The goal of this work is the computation of very compact binary hashes forimage instance retrieval. Our approach has two novel contributions. The firstone is Nested Invariance Pooling (NIP), a method inspired from i-theory, amathematical theory for computing group invariant transformations withfeed-forward neural networks. NIP is able to produce compact andwell-performing descriptors with visual representations extracted fromconvolutional neural networks. We specifically incorporate scale, translationand rotation invariances but the scheme can be extended to any arbitrary setsof transformations. We also show that using moments of increasing orderthroughout nesting is important. The NIP descriptors are then hashed to thetarget code size (32-256 bits) with a Restricted Boltzmann Machine with a novelbatch-level regularization scheme specifically designed for the purpose ofhashing (RBMH). A thorough empirical evaluation with state-of-the-art showsthat the results obtained both with the NIP descriptors and the NIP+RBMH hashesare consistently outstanding across a wide range of datasets.

Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval