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

Feature detection is an important procedure for image matching, whereunsupervised feature detection methods are the detection approaches that havebeen mostly studied recently, including the ones that are based onrepeatability requirement to define loss functions, and the ones that attemptto use descriptor matching to drive the optimization of the pipelines. For theformer type, mean square error (MSE) is usually used which cannot providestrong constraint for training and can make the model easy to be stuck into thecollapsed solution. For the later one, due to the down sampling operation andthe expansion of receptive fields, the details can be lost for localdescriptors can be lost, making the constraint not fine enough. Considering theissues above, we propose to combine both ideas, which including three aspects.1) We propose to achieve fine constraint based on the requirement ofrepeatability while coarse constraint with guidance of deep convolutionfeatures. 2) To address the issue that optimization with MSE is limited,entropy-based cost function is utilized, both soft cross-entropy andself-information. 3) With the guidance of convolution features, we define thecost function from both positive and negative sides. Finally, we study theeffect of each modification proposed and experiments demonstrate that ourmethod achieves competitive results over the state-of-the-art approaches.

Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy Optimization for Salient Points