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

Although 3D human pose estimation has gained impressive development in recentyears, only a few works focus on infants, that have different bone lengths andalso have limited data. Directly applying adult pose estimation modelstypically achieves low performance in the infant domain and suffers fromout-of-distribution issues. Moreover, the limitation of infant pose datacollection also heavily constrains the efficiency of learning-based models tolift 2D poses to 3D. To deal with the issues of small datasets, domainadaptation and data augmentation are commonly used techniques. Following thisparadigm, we take advantage of an optimization-based method that utilizesgenerative priors to predict 3D infant keypoints from 2D keypoints without theneed of large training data. We further apply a guided diffusion model todomain adapt 3D adult pose to infant pose to supplement small datasets.Besides, we also prove that our method, ZeDO-i, could attain efficient domainadaptation, even if only a small number of data is given. Quantitatively, weclaim that our model attains state-of-the-art MPJPE performance of 43.6 mm onthe SyRIP dataset and 21.2 mm on the MINI-RGBD dataset.

Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation