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 present a GAN-based Transformer for general action-conditioned 3D humanmotion generation, including not only single-person actions but alsomulti-person interactive actions. Our approach consists of a powerfulAction-conditioned motion TransFormer (ActFormer) under a GAN training scheme,equipped with a Gaussian Process latent prior. Such a design combines thestrong spatio-temporal representation capacity of Transformer, superiority ingenerative modeling of GAN, and inherent temporal correlations from the latentprior. Furthermore, ActFormer can be naturally extended to multi-person motionsby alternately modeling temporal correlations and human interactions withTransformer encoders. To further facilitate research on multi-person motiongeneration, we introduce a new synthetic dataset of complex multi-person combatbehaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and theproposed combat dataset show that our method can adapt to various human motionrepresentations and achieve superior performance over the state-of-the-artmethods on both single-person and multi-person motion generation tasks,demonstrating a promising step towards a general human motion generator.

ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation