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

Event cameras are novel bio-inspired sensors, which asynchronously capturepixel-level intensity changes in the form of "events". The innovative way theyacquire data presents several advantages over standard devices, especially inpoor lighting and high-speed motion conditions. However, the novelty of thesesensors results in the lack of a large amount of training data capable of fullyunlocking their potential. The most common approach implemented by researchersto address this issue is to leverage simulated event data. Yet, this approachcomes with an open research question: how well simulated data generalize toreal data? To answer this, we propose to exploit, in the event-based context,recent Domain Adaptation (DA) advances in traditional computer vision, showingthat DA techniques applied to event data help reduce the sim-to-real gap. Tothis purpose, we propose a novel architecture, which we call Multi-View DA4E(MV-DA4E), that better exploits the peculiarities of frame-based eventrepresentations while also promoting domain invariant characteristics infeatures. Through extensive experiments, we prove the effectiveness of DAmethods and MV-DA4E on N-Caltech101. Moreover, we validate their soundness in areal-world scenario through a cross-domain analysis on the popular RGB-D ObjectDataset (ROD), which we extended to the event modality (RGB-E).

DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation