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/

Zendy Plus

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

Zendy Tools

Zendy Open

Diverse human motion prediction aims at predicting multiple possible futurepose sequences from a sequence of observed poses. Previous approaches usuallyemploy deep generative networks to model the conditional distribution of data,and then randomly sample outcomes from the distribution. While differentresults can be obtained, they are usually the most likely ones which are notdiverse enough. Recent work explicitly learns multiple modes of the conditionaldistribution via a deterministic network, which however can only cover a fixednumber of modes within a limited range. In this paper, we propose a novelsampling strategy for sampling very diverse results from an imbalancedmultimodal distribution learned by a deep generative model. Our method works bygenerating an auxiliary space and smartly making randomly sampling from theauxiliary space equivalent to the diverse sampling from the targetdistribution. We propose a simple yet effective network architecture thatimplements this novel sampling strategy, which incorporates a Gumbel-Softmaxcoefficient matrix sampling method and an aggressive diversity promoting hingeloss function. Extensive experiments demonstrate that our method significantlyimproves both the diversity and accuracy of the samplings compared withprevious state-of-the-art sampling approaches. Code and pre-trained models areavailable at https://github.com/Droliven/diverse_sampling.

Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space