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

Visual recognition inside the vehicle cabin leads to safer driving and moreintuitive human-vehicle interaction but such systems face substantial obstaclesas they need to capture different granularities of driver behaviour whiledealing with highly limited body visibility and changing illumination.Multimodal recognition mitigates a number of such issues: prediction outcomesof different sensors complement each other due to different modality-specificstrengths and weaknesses. While several late fusion methods have beenconsidered in previously published frameworks, they constantly featuredifferent architecture backbones and building blocks making it very hard toisolate the role of the chosen late fusion strategy itself. This paper presentsan empirical evaluation of different paradigms for decision-level late fusionin video-based driver observation. We compare seven different mechanisms forjoining the results of single-modal classifiers which have been both popular,(e.g. score averaging) and not yet considered (e.g. rank-level fusion) in thecontext of driver observation evaluating them based on different criteria andbenchmark settings. This is the first systematic study of strategies for fusingoutcomes of multimodal predictors inside the vehicles, conducted with the goalto provide guidance for fusion scheme selection.

A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding