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

3D hand-object pose estimation is an important issue to understand theinteraction between human and environment. Current hand-object pose estimationmethods require detailed 3D labels, which are expensive and labor-intensive. Totackle the problem of data collection, we propose a semi-supervised 3Dhand-object pose estimation method with two key techniques: pose dictionarylearning and an object-oriented coordinate system. The proposed pose dictionarylearning module can distinguish infeasible poses by reconstruction error,enabling unlabeled data to provide supervision signals. The proposedobject-oriented coordinate system can make 3D estimations equivariant to thecamera perspective. Experiments are conducted on FPHA and HO-3D datasets. Ourmethod reduces estimation error by 19.5% / 24.9% for hands/objects compared tostraightforward use of labeled data on FPHA and outperforms several baselinemethods. Extensive experiments also validate the robustness of the proposedmethod.

Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learning