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

We consider the problem of comparing the similarity of image sets withvariable-quantity, quality and un-ordered heterogeneous images. We use featurerestructuring to exploit the correlations of both inner$\&$inter-set images.Specifically, the residual self-attention can effectively restructure thefeatures using the other features within a set to emphasize the discriminativeimages and eliminate the redundancy. Then, a sparse/collaborativelearning-based dependency-guided representation scheme reconstructs the probefeatures conditional to the gallery features in order to adaptively align thetwo sets. This enables our framework to be compatible with both verificationand open-set identification. We show that the parametric self-attention networkand non-parametric dictionary learning can be trained end-to-end by a unifiedalternative optimization scheme, and that the full framework ispermutation-invariant. In the numerical experiments we conducted, our methodachieves top performance on competitive image set/video-based face recognitionand person re-identification benchmarks.

Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition