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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We consider the problem of modeling the dynamics of continuousspatial-temporal processes represented by irregular samples through both spaceand time. Such processes occur in sensor networks, citizen science, multi-robotsystems, and many others. We propose a new deep model that is able to directlylearn and predict over this irregularly sampled data, without voxelization, byleveraging a recent convolutional architecture for static point clouds. Themodel also easily incorporates the notion of multiple entities in the process.In particular, the model can flexibly answer prediction queries about arbitraryspace-time points for different entities regardless of the distribution of thetraining or test-time data. We present experiments on real-world weatherstation data and battles between large armies in StarCraft II. The resultsdemonstrate the model's flexibility in answering a variety of query types anddemonstrate improved performance and efficiency compared to state-of-the-artbaselines.

Deep Convolution for Irregularly Sampled Temporal Point Clouds