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

2D+3D facial expression recognition (FER) can effectively cope withillumination changes and pose variations by simultaneously merging 2D textureand more robust 3D depth information. Most deep learning-based approachesemploy the simple fusion strategy that concatenates the multimodal featuresdirectly after fully-connected layers, without considering the differentdegrees of significance for each modality. Meanwhile, how to focus on both 2Dand 3D local features in salient regions is still a great challenge. In thisletter, we propose the adaptive fusion network with masks (AFNet-M) for 2D+3DFER. To enhance 2D and 3D local features, we take the masks annotating salientregions of the face as prior knowledge and design the mask attention module(MA) which can automatically learn two modulation vectors to adjust the featuremaps. Moreover, we introduce a novel fusion strategy that can perform adaptivefusion at convolutional layers through the designed importance weightscomputing module (IWC). Experimental results demonstrate that our AFNet-Machieves the state-of-the-art performance on BU-3DFE and Bosphorus datasets andrequires fewer parameters in comparison with other models.

AFNet-M: Adaptive Fusion Network with Masks for 2D+3D Facial Expression Recognition