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

We propose an end-to-end unified 3D mesh recovery of humans and quadrupedanimals trained in a weakly-supervised way. Unlike recent work focusing on asingle target class only, we aim to recover 3D mesh of broader classes with asingle multi-task model. However, there exists no dataset that can directlyenable multi-task learning due to the absence of both human and animalannotations for a single object, e.g., a human image does not have animal poseannotations; thus, we have to devise a new way to exploit heterogeneousdatasets. To make the unstable disjoint multi-task learning jointly trainable,we propose to exploit the morphological similarity between humans and animals,motivated by animal exercise where humans imitate animal poses. We realize themorphological similarity by semantic correspondences, called sub-keypoint,which enables joint training of human and animal mesh regression branches.Besides, we propose class-sensitive regularization methods to avoid amean-shape bias and to improve the distinctiveness across multi-classes. Ourmethod performs favorably against recent uni-modal models on various human andanimal datasets while being far more compact.

Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise