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

Human-object interaction (HOI) detection for capturing relationships betweenhumans and objects is an important task in the semantic understanding ofimages. When processing human and object keypoints extracted from an imageusing a graph convolutional network (GCN) to detect HOI, it is crucial toextract appropriate object keypoints regardless of the object type and todesign a GCN that accurately captures the spatial relationships betweenkeypoints. This paper presents the human and object keypoint-based extensionmodule (HOKEM) as an easy-to-use extension module to improve the accuracy ofthe conventional detection models. The proposed object keypoint extractionmethod is simple yet accurately represents the shapes of various objects.Moreover, the proposed human-object adaptive GCN (HO-AGCN), which introducesadaptive graph optimization and attention mechanism, accurately captures thespatial relationships between keypoints. Experiments using the HOI dataset,V-COCO, showed that HOKEM boosted the accuracy of an appearance-based model bya large margin.

HOKEM: Human and Object Keypoint-based Extension Module for Human-Object Interaction Detection