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 introduce a novel loss for learning local feature descriptors which isinspired by the Lowe's matching criterion for SIFT. We show that the proposedloss that maximizes the distance between the closest positive and closestnegative patch in the batch is better than complex regularization methods; itworks well for both shallow and deep convolution network architectures.Applying the novel loss to the L2Net CNN architecture results in a compactdescriptor -- it has the same dimensionality as SIFT (128) that showsstate-of-art performance in wide baseline stereo, patch verification andinstance retrieval benchmarks. It is fast, computing a descriptor takes about 1millisecond on a low-end GPU.

Working hard to know your neighbor's margins: Local descriptor learning loss