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

Keypoint detection and description is fundamental yet important in manyvision applications. Most existing methods use detect-then-describe ordetect-and-describe strategy to learn local features without considering theircontext information. Consequently, it is challenging for these methods to learnrobust local features. In this paper, we focus on the fusion of low-leveltextual information and high-level semantic context information to improve thediscrimitiveness of local features. Specifically, we first estimate a score mapto represent the distribution of potential keypoints according to the qualityof descriptors of all pixels. Then, we extract and aggregate multi-scalehigh-level semantic features based by the guidance of the score map. Finally,the low-level local features and high-level semantic features are fused andrefined using a residual module. Experiments on the challenging local featurebenchmark dataset demonstrate that our method achieves the state-of-the-artperformance in the local feature challenge of the visual localizationbenchmark.

Learning Local Features with Context Aggregation for Visual Localization