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

In this paper we propose a new approach for learning local descriptors formatching image patches. It has recently been demonstrated that descriptorsbased on convolutional neural networks (CNN) can significantly improve thematching performance. Unfortunately their computational complexity isprohibitive for any practical application. We address this problem and proposea CNN based descriptor with improved matching performance, significantlyreduced training and execution time, as well as low dimensionality.  We propose to train the network with triplets of patches that include apositive and negative pairs. To that end we introduce a new loss function thatexploits the relations within the triplets. We compare our approach to recentlyintroduced MatchNet and DeepCompare and demonstrate the advantages of ourdescriptor in terms of performance, memory footprint and speed i.e. when run inGPU, the extraction time of our 128 dimensional feature is comparable to thefastest available binary descriptors such as BRIEF and ORB.

PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors