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

Geo-tagged images are publicly available in large quantities, whereas labelssuch as object classes are rather scarce and expensive to collect. Meanwhile,contrastive learning has achieved tremendous success in various natural imageand language tasks with limited labeled data. However, existing methods fail tofully leverage geospatial information, which can be paramount to distinguishingobjects that are visually similar. To directly leverage the abundant geospatialinformation associated with images in pre-training, fine-tuning, and inferencestages, we present Contrastive Spatial Pre-Training (CSP), a self-supervisedlearning framework for geo-tagged images. We use a dual-encoder to separatelyencode the images and their corresponding geo-locations, and use contrastiveobjectives to learn effective location representations from images, which canbe transferred to downstream supervised tasks such as image classification.Experiments show that CSP can improve model performance on both iNat2018 andfMoW datasets. Especially, on iNat2018, CSP significantly boosts the modelperformance with 10-34% relative improvement with various labeled training datasampling ratios.

CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations