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

Given a set of hand-crafted local features, acquiring a global representationvia aggregation is a promising technique to boost computational efficiency andimprove task performance. Existing feature aggregation (FA) approaches,including Bag of Words and Fisher Vectors, usually fail to capture the desiredinformation due to their pipeline mode. In this paper, we propose a genericformulation to provide a systematical solution (named ProLFA) to aggregatelocal descriptors. It is capable of producing compact yet interpretablerepresentations by selecting representative prototypes from numerousdescriptors, under relaxed exclusivity constraint. Meanwhile, to strengthen thediscriminability of the aggregated representation, we rationally enforce thedomain-invariant projection of bundled descriptors along a task-specificdirection. Furthermore, ProLFA is also provided with a powerful generalizationability to deal flexibly with the semi-supervised and fully supervisedscenarios in local feature aggregation. Experimental results on variousdescriptors and tasks demonstrate that the proposed ProLFA is considerablysuperior over currently available alternatives about feature aggregation.

ProLFA: Representative Prototype Selection for Local Feature Aggregation