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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present a novel autoregression network to generate virtual agents thatconvey various emotions through their walking styles or gaits. Given the 3Dpose sequences of a gait, our network extracts pertinent movement features andaffective features from the gait. We use these features to synthesizesubsequent gaits such that the virtual agents can express and transitionbetween emotions represented as combinations of happy, sad, angry, and neutral.We incorporate multiple regularizations in the training of our network tosimultaneously enforce plausible movements and noticeable emotions on thevirtual agents. We also integrate our approach with an AR environment using aMicrosoft HoloLens and can generate emotive gaits at interactive rates toincrease the social presence. We evaluate how human observers perceive both thenaturalness and the emotions from the generated gaits of the virtual agents ina web-based study. Our results indicate around 89% of the users found thenaturalness of the gaits satisfactory on a five-point Likert scale, and theemotions they perceived from the virtual agents are statistically similar tothe intended emotions of the virtual agents. We also use our network to augmentexisting gait datasets with emotive gaits and will release this augmenteddataset for future research in emotion prediction and emotive gait synthesis.Our project website is available at https://gamma.umd.edu/gen_emotive_gaits/.

Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression