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

From medical research to gaming applications, gaze estimation is becoming avaluable tool. While there exists a number of hardware-based solutions, recentdeep learning-based approaches, coupled with the availability of large-scaledatabases, have allowed to provide a precise gaze estimate using only consumersensors. However, there remains a number of questions, regarding the problemformulation, architectural choices and learning paradigms for designing gazeestimation systems in order to bridge the gap between geometry-based systemsinvolving specific hardware and approaches using consumer sensors only. In thispaper, we introduce a deep, end-to-end trainable ensemble of heatmap-based weakpredictors for 2D/3D gaze estimation. We show that, through heterogeneousarchitectural design of these weak predictors, we can improve the decorrelationbetween the latter predictors to design more robust deep ensemble models.Furthermore, we propose a stochastic combinatory loss that consists in randomlysampling combinations of weak predictors at train time. This allows to trainbetter individual weak predictors, with lower correlation between them. This,in turns, allows to significantly enhance the performance of the deep ensemble.We show that our Deep heterogeneous ensemble with Stochastic Combinatory loss(DeeSCo) outperforms state-of-the-art approaches for 2D/3D gaze estimation onmultiple datasets.

DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation