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

Image cropping aims to improve the composition as well as aesthetic qualityof an image by removing extraneous content from it. Most of the existing imagecropping databases provide only one or several human-annotated bounding boxesas the groundtruths, which can hardly reflect the non-uniqueness andflexibility of image cropping in practice. The employed evaluation metrics suchas intersection-over-union cannot reliably reflect the real performance of acropping model, either. This work revisits the problem of image cropping, andpresents a grid anchor based formulation by considering the special propertiesand requirements (e.g., local redundancy, content preservation, aspect ratio)of image cropping. Our formulation reduces the searching space of candidatecrops from millions to no more than ninety. Consequently, a grid anchor basedcropping benchmark is constructed, where all crops of each image are annotatedand more reliable evaluation metrics are defined. To meet the practical demandsof robust performance and high efficiency, we also design an effective andlightweight cropping model. By simultaneously considering the region ofinterest and region of discard, and leveraging multi-scale information, ourmodel can robustly output visually pleasing crops for images of differentscenes. With less than 2.5M parameters, our model runs at a speed of 200 FPS onone single GTX 1080Ti GPU and 12 FPS on one i7-6800K CPU. The code is availableat: \url{https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping-Pytorch}.

Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model