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

Learning based feature matching methods have been commonly studied in recentyears. The core issue for learning feature matching is to how to learn (1)discriminative representations for feature points (or regions) within eachintra-image and (2) consensus representations for feature points acrossinter-images. Recently, self- and cross-attention models have been exploited toaddress this issue. However, in many scenes, features are coming withlarge-scale, redundant and outliers contaminated. Previousself-/cross-attention models generally conduct message passing on all primalfeatures which thus lead to redundant learning and high computational cost. Tomitigate limitations, inspired by recent seed matching methods, in this paper,we propose a novel efficient Anchor Matching Transformer (AMatFormer) for thefeature matching problem. AMatFormer has two main aspects: First, it mainlyconducts self-/cross-attention on some anchor features and leverages theseanchor features as message bottleneck to learn the representations for allprimal features. Thus, it can be implemented efficiently and compactly. Second,AMatFormer adopts a shared FFN module to further embed the features of twoimages into the common domain and thus learn the consensus featurerepresentations for the matching problem. Experiments on several benchmarksdemonstrate the effectiveness and efficiency of the proposed AMatFormermatching approach.

AMatFormer: Efficient Feature Matching via Anchor Matching Transformer