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

Social robots able to continually learn facial expressions couldprogressively improve their emotion recognition capability towards peopleinteracting with them. Semi-supervised learning through ensemble predictions isan efficient strategy to leverage the high exposure of unlabelled facialexpressions during human-robot interactions. Traditional ensemble-basedsystems, however, are composed of several independent classifiers leading to ahigh degree of redundancy, and unnecessary allocation of computationalresources. In this paper, we proposed an ensemble based on convolutionalnetworks where the early layers are strong low-level feature extractors, andtheir representations shared with an ensemble of convolutional branches. Thisresults in a significant drop in redundancy of low-level features processing.Training in a semi-supervised setting, we show that our approach is able tocontinually learn facial expressions through ensemble predictions usingunlabelled samples from different data distributions.

An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions