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

In 2D+3D facial expression recognition (FER), existing methods generatemulti-view geometry maps to enhance the depth feature representation. However,this may introduce false estimations due to local plane fitting from incompletepoint clouds. In this paper, we propose a novel Map Generation technique fromthe viewpoint of information theory, to boost the slight 3D expressiondifferences from strong personality variations. First, we examine the HDR depthdata to extract the discriminative dynamic range $r_{dis}$, and maximize theentropy of $r_{dis}$ to a global optimum. Then, to prevent the largedeformation caused by over-enhancement, we introduce a depth distortionconstraint and reduce the complexity from $O(KN^2)$ to $O(KN\tau)$.Furthermore, the constrained optimization is modeled as a $K$-edges maximumweight path problem in a directed acyclic graph, and we solve it efficientlyvia dynamic programming. Finally, we also design an efficient Facial Attentionstructure to automatically locate subtle discriminative facial parts formulti-scale learning, and train it with a proposed loss function$\mathcal{L}_{FA}$ without any facial landmarks. Experimental results ondifferent datasets show that the proposed method is effective and outperformsthe state-of-the-art 2D+3D FER methods in both FER accuracy and the outputentropy of the generated maps.

2D+3D Facial Expression Recognition via Discriminative Dynamic Range Enhancement and Multi-Scale Learning