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

State-of-the-art machine-learning methods for event cameras treat events asdense representations and process them with conventional deep neural networks.Thus, they fail to maintain the sparsity and asynchronous nature of event data,thereby imposing significant computation and latency constraints on downstreamsystems. A recent line of work tackles this issue by modeling events asspatiotemporally evolving graphs that can be efficiently and asynchronouslyprocessed using graph neural networks. These works showed impressivecomputation reductions, yet their accuracy is still limited by the small scaleand shallow depth of their network, both of which are required to reducecomputation. In this work, we break this glass ceiling by introducing severalarchitecture choices which allow us to scale the depth and complexity of suchmodels while maintaining low computation. On object detection tasks, oursmallest model shows up to 3.7 times lower computation, while outperformingstate-of-the-art asynchronous methods by 7.4 mAP. Even when scaling to largermodel sizes, we are 13% more efficient than state-of-the-art whileoutperforming it by 11.5 mAP. As a result, our method runs 3.7 times fasterthan a dense graph neural network, taking only 8.4 ms per forward pass. Thisopens the door to efficient, and accurate object detection in edge-casescenarios.

Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras