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

Gesture recognition is a foundational task in human-machine interaction(HMI). While there has been significant progress in gesture recognition basedon surface electromyography (sEMG), accurate recognition of predefined gesturesonly within a closed set is still inadequate in practice. It is essential toeffectively discern and reject unknown gestures of disinterest in a robustsystem. Numerous methods based on prototype learning (PL) have been proposed totackle this open set recognition (OSR) problem. However, they do not fullyexplore the inherent distinctions between known and unknown classes. In thispaper, we propose a more effective PL method leveraging two novel and inherentdistinctions, feature activation level and projection inconsistency.Specifically, the Feature Activation Enhancement Mechanism (FAEM) widens thegap in feature activation values between known and unknown classes.Furthermore, we introduce Orthogonal Prototype Learning (OPL) to constructmultiple perspectives. OPL acts to project a sample from orthogonal directionsto maximize the distinction between its two projections, where unknown sampleswill be projected near the clusters of different known classes while knownsamples still maintain intra-class similarity. Our proposed methodsimultaneously achieves accurate closed-set classification for predefinedgestures and effective rejection for unknown gestures. Extensive experimentsdemonstrate its efficacy and superiority in open-set gesture recognition basedon sEMG.

Towards Open-set Gesture Recognition via Feature Activation Enhancement and Orthogonal Prototype Learning