GeoConv: Geodesic Guided Convolution for Facial Action Unit Recognition

doi:doi:10.57702/48c8gqv6

GeoConv: Geodesic Guided Convolution for Facial Action Unit Recognition

Automatic facial action unit (AU) recognition has attracted great attention but still remains a challenging task, as subtle changes of local facial muscles are difficult to thoroughly capture. Most existing AU recognition approaches leverage geometry information in a straightfor-ward 2D or 3D manner, which either ignore 3D manifold information or suffer from high computational costs.

BibTex:

@dataset{Yuedong_Chen_and_Guoxian_Song_and_Zhiwen_Shao_and_Jianfei_Cai_and_Tat-Jen_Cham_and_Jianmin_Zheng_2024,
    abstract = {Automatic facial action unit (AU) recognition has attracted great attention but still remains a challenging task, as subtle changes of local facial muscles are difficult to thoroughly capture. Most existing AU recognition approaches leverage geometry information in a straightfor-ward 2D or 3D manner, which either ignore 3D manifold information or suffer from high computational costs.},
    author = {Yuedong Chen and Guoxian Song and Zhiwen Shao and Jianfei Cai and Tat-Jen Cham and Jianmin Zheng},
    doi = {10.57702/48c8gqv6},
    institution = {No Organization},
    keyword = {'3D Morphable Model', 'Facial Action Unit Recognition', 'Geodesic Guided Convolution'},
    month = {dec},
    publisher = {TIB},
    title = {GeoConv: Geodesic Guided Convolution for Facial Action Unit Recognition},
    url = {https://service.tib.eu/ldmservice/dataset/geoconv--geodesic-guided-convolution-for-facial-action-unit-recognition},
    year = {2024}
}