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

Learning compact binary codes for image retrieval task using deep neuralnetworks has attracted increasing attention recently. However, training deephashing networks for the task is challenging due to the binary constraints onthe hash codes, the similarity preserving property, and the requirement for avast amount of labelled images. To the best of our knowledge, none of theexisting methods has tackled all of these challenges completely in a unifiedframework. In this work, we propose a novel end-to-end deep learning approachfor the task, in which the network is trained to produce binary codes directlyfrom image pixels without the need of manual annotation. In particular, to dealwith the non-smoothness of binary constraints, we propose a novel pairwiseconstrained loss function, which simultaneously encodes the distances betweenpairs of hash codes, and the binary quantization error. In order to train thenetwork with the proposed loss function, we propose an efficient parameterlearning algorithm. In addition, to provide similar / dissimilar trainingimages to train the network, we exploit 3D models reconstructed from unlabelledimages for automatic generation of enormous training image pairs. The extensiveexperiments on image retrieval benchmark datasets demonstrate the improvementsof the proposed method over the state-of-the-art compact representation methodson the image retrieval problem.

Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation