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

Inertial information processing plays a pivotal role in ego-motion awarenessfor mobile agents, as inertial measurements are entirely egocentric and notenvironment dependent. However, they are affected greatly by changes in sensorplacement/orientation or motion dynamics, and it is infeasible to collectlabelled data from every domain. To overcome the challenges of domainadaptation on long sensory sequences, we propose a novel framework thatextracts domain-invariant features of raw sequences from arbitrary domains, andtransforms to new domains without any paired data. Through the experiments, wedemonstrate that it is able to efficiently and effectively convert the rawsequence from a new unlabelled target domain into an accurate inertialtrajectory, benefiting from the physical motion knowledge transferred from thelabelled source domain. We also conduct real-world experiments to show ourframework can reconstruct physically meaningful trajectories from raw IMUmeasurements obtained with a standard mobile phone in various attachments.

Transferring Physical Motion Between Domains for Neural Inertial Tracking