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 present a novel deep architecture termed templateNet for depth basedobject instance recognition. Using an intermediate template layer we exploitprior knowledge of an object's shape to sparsify the feature maps. This hasthree advantages: (i) the network is better regularised resulting in structuredfilters; (ii) the sparse feature maps results in intuitive features been learntwhich can be visualized as the output of the template layer and (iii) theresulting network achieves state-of-the-art performance. The network benefitsfrom this without any additional parametrization from the template layer. Wederive the weight updates needed to efficiently train this network in anend-to-end manner. We benchmark the templateNet for depth based object instancerecognition using two publicly available datasets. The datasets presentmultiple challenges of clutter, large pose variations and similar lookingdistractors. Through our experiments we show that with the addition of atemplate layer, a depth based CNN is able to outperform existingstate-of-the-art methods in the field.

TemplateNet for Depth-Based Object Instance Recognition