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

Models of human motion commonly focus either on trajectory prediction oraction classification but rarely both. The marked heterogeneity and intricatecompositionality of human motion render each task vulnerable to the datadegradation and distributional shift common to real-world scenarios. Asufficiently expressive generative model of action could in theory enable dataconditioning and distributional resilience within a unified frameworkapplicable to both tasks. Here we propose a novel architecture based onhierarchical variational autoencoders and deep graph convolutional neuralnetworks for generating a holistic model of action over multiple time-scales.We show this Hierarchical Graph-convolutional Variational Autoencoder (HG-VAE)to be capable of generating coherent actions, detecting out-of-distributiondata, and imputing missing data by gradient ascent on the model's posterior.Trained and evaluated on H3.6M and the largest collection of open source humanmotion data, AMASS, we show HG-VAE can facilitate downstream discriminativelearning better than baseline models.

Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion