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

The workflow of extracting features from images using convolutional neuralnetworks (CNN) and generating captions with recurrent neural networks (RNN) hasbecome a de-facto standard for image captioning task. However, since CNNfeatures are originally designed for classification task, it is mostlyconcerned with the main conspicuous element of the image, and often fails tocorrectly convey information on local, secondary elements. We propose toincorporate coding with vector of locally aggregated descriptors (VLAD) onspatial pyramid for CNN features of sub-regions in order to generate imagerepresentations that better reflect the local information of the images. Ourresults show that our method of compact VLAD coding can match CNN features withas little as 3% of dimensionality and, when combined with spatial pyramid, itresults in image captions that more accurately take local elements intoaccount.

Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning