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 the multi-layer extension of the Sparse Ternary Codes (STC) forfast similarity search where we focus on the reconstruction of the databasevectors from the ternary codes. To consider the trade-offs between thecompactness of the STC and the quality of the reconstructed vectors, we studythe rate-distortion behavior of these codes under different setups. We showthat a single-layer code cannot achieve satisfactory results at high rates.Therefore, we extend the concept of STC to multiple layers and design theML-STC, a codebook-free system that successively refines the reconstruction ofthe residuals of previous layers. While the ML-STC keeps the sparse ternarystructure of the single-layer STC and hence is suitable for fast similaritysearch in large-scale databases, we show its superior rate-distortionperformance on both model-based synthetic data and public large-scaledatabases, as compared to several binary hashing methods.

A multi-layer network based on Sparse Ternary Codes for universal vector compression