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

Deep hashing has been widely applied to large-scale image retrieval tasksowing to efficient computation and low storage cost by encodinghigh-dimensional image data into binary codes. Since binary codes do notcontain as much information as float features, the essence of binary encodingis preserving the main context to guarantee retrieval quality. However, theexisting hashing methods have great limitations on suppressing redundantbackground information and accurately encoding from Euclidean space to Hammingspace by a simple sign function. In order to solve these problems, aCross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in thispaper. Firstly, we design a two-branch framework to capture fine-grained localinformation while maintaining high-level global semantic information. Besides,Attention guided Information Extraction module (AIE) is introduced between twobranches, which suppresses areas of low context information cooperated withglobal sliding windows. Unlike previous methods, our CSCE-Net learns acontent-related Dynamic Sign Function (DSF) to replace the original simple signfunction. Therefore, the proposed CSCE-Net is context-sensitive and able toperform well on accurate image binary encoding. We further demonstrate that ourCSCE-Net is superior to the existing hashing methods, which improves retrievalperformance on standard benchmarks.

Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding