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

Previous methods for dynamic facial expression recognition (DFER) in the wildare mainly based on Convolutional Neural Networks (CNNs), whose localoperations ignore the long-range dependencies in videos. Transformer-basedmethods for DFER can achieve better performances but result in higher FLOPs andcomputational costs. To solve these problems, the local-global spatio-temporalTransformer (LOGO-Former) is proposed to capture discriminative features withineach frame and model contextual relationships among frames while balancing thecomplexity. Based on the priors that facial muscles move locally and facialexpressions gradually change, we first restrict both the space attention andthe time attention to a local window to capture local interactions amongfeature tokens. Furthermore, we perform the global attention by querying atoken with features from each local window iteratively to obtain long-rangeinformation of the whole video sequence. In addition, we propose the compactloss regularization term to further encourage the learned features have theminimum intra-class distance and the maximum inter-class distance. Experimentson two in-the-wild dynamic facial expression datasets (i.e., DFEW and FERV39K)indicate that our method provides an effective way to make use of the spatialand temporal dependencies for DFER.

LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition