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

In this paper, we consider the problem of descriptors construction for thetask of content-based image retrieval using deep neural networks. The idea ofneural codes, based on fully connected layers activations, is extended byincorporating the information contained in convolutional layers. It is knownthat the total number of neurons in the convolutional part of the network islarge and the majority of them have little influence on the finalclassification decision. Therefore, in the paper we propose a novel algorithmthat allows us to extract the most significant neuron activations and utilizethis information to construct effective descriptors. The descriptors consistingof values taken from both the fully connected and convolutional layersperfectly represent the whole image content. The images retrieved using thesedescriptors match semantically very well to the query image, and also they aresimilar in other secondary image characteristics, like background, textures orcolor distribution. These features of the proposed descriptors are verifiedexperimentally based on the IMAGENET1M dataset using the VGG16 neural network.

A new approach to descriptors generation for image retrieval by analyzing activations of deep neural network layers