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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Learning how humans manipulate objects requires machines to acquire knowledgefrom two perspectives: one for understanding object affordances and the otherfor learning human's interactions based on the affordances. Even though thesetwo knowledge bases are crucial, we find that current databases lack acomprehensive awareness of them. In this work, we propose a multi-modal andrich-annotated knowledge repository, OakInk, for visual and cognitiveunderstanding of hand-object interactions. We start to collect 1,800 commonhousehold objects and annotate their affordances to construct the firstknowledge base: Oak. Given the affordance, we record rich human interactionswith 100 selected objects in Oak. Finally, we transfer the interactions on the100 recorded objects to their virtual counterparts through a novel method:Tink. The recorded and transferred hand-object interactions constitute thesecond knowledge base: Ink. As a result, OakInk contains 50,000 distinctaffordance-aware and intent-oriented hand-object interactions. We benchmarkOakInk on pose estimation and grasp generation tasks. Moreover, we propose twopractical applications of OakInk: intent-based interaction generation andhandover generation. Our datasets and source code are publicly available athttps://github.com/lixiny/OakInk.

OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction