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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper addresses the problem of learning word image representations:given the cropped image of a word, we are interested in finding a descriptive,robust, and compact fixed-length representation. Machine learning techniquescan then be supplied with these representations to produce models useful forword retrieval or recognition tasks. Although many works have focused on themachine learning aspect once a global representation has been produced, littlework has been devoted to the construction of those base image representations:most works use standard coding and aggregation techniques directly on top ofstandard computer vision features such as SIFT or HOG.  We propose to learn local mid-level features suitable for building word imagerepresentations. These features are learnt by leveraging character bounding boxannotations on a small set of training images. However, contrary to otherapproaches that use character bounding box information, our approach does notrely on detecting the individual characters explicitly at testing time. Ourlocal mid-level features can then be aggregated to produce a global word imagesignature. When pairing these features with the recent word attributesframework of Almaz\'an et al., we obtain results comparable with or better thanthe state-of-the-art on matching and recognition tasks using global descriptorsof only 96 dimensions.

Supervised mid-level features for word image representation