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 propose a new method for fine-grained few-shot recognition via deep objectparsing. In our framework, an object is made up of K distinct parts and foreach part, we learn a dictionary of templates, which is shared across allinstances and categories. An object is parsed by estimating the locations ofthese K parts and a set of active templates that can reconstruct the partfeatures. We recognize test instances by comparing its active templates and therelative geometry of its part locations against those of the presented few-shotinstances. Our method is end-to-end trainable to learn part templates on-top ofa convolutional backbone. To combat visual distortions such as orientation,pose and size, we learn templates at multiple scales, and at test-time parseand match instances across these scales. We show that our method is competitivewith the state-of-the-art, and by virtue of parsing enjoys interpretability aswell.

Fine-grained Few-shot Recognition by Deep Object Parsing