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 approach for forecasting video of complex human activityinvolving multiple people. Direct pixel-level prediction is too simple tohandle the appearance variability in complex activities. Hence, we developnovel intermediate representations. An architecture combining a hierarchicaltemporal model for predicting human poses and encoder-decoder convolutionalneural networks for rendering target appearances is proposed. Our hierarchicalmodel captures interactions among people by adopting a dynamic group-basedinteraction mechanism. Next, our appearance rendering network encodes thetargets' appearances by learning adaptive appearance filters using a fullyconvolutional network. Finally, these filters are placed in encoder-decoderneural networks to complete the rendering. We demonstrate that our model cangenerate videos that are superior to state-of-the-art methods, and can handlecomplex human activity scenarios in video forecasting.

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering