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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Sparse coding with dictionary learning (DL) has shown excellentclassification performance. Despite the considerable number of existing works,how to obtain features on top of which dictionaries can be better learnedremains an open and interesting question. Many current prevailing DL methodsdirectly adopt well-performing crafted features. While such strategy mayempirically work well, it ignores certain intrinsic relationship betweendictionaries and features. We propose a framework where features anddictionaries are jointly learned and optimized. The framework, named jointnon-negative projection and dictionary learning (JNPDL), enables interactionbetween the input features and the dictionaries. The non-negative projectionleads to discriminative parts-based object features while DL seeks a moresuitable representation. Discriminative graph constraints are further imposedto simultaneously maximize intra-class compactness and inter-classseparability. Experiments on both image and image set classification show theexcellent performance of JNPDL by outperforming several state-of-the-artapproaches.

Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification