Audio-Visual Active Speaker Identification: A comparison of dense image-based features and sparse facial landmark-based features

Warre Geeroms, Gianni Allebosch, Stijn Kindt, Loubna Kadri, Peter Veelaert, Nilesh Madhu. Audio-Visual Active Speaker Identification: A comparison of dense image-based features and sparse facial landmark-based features. In Sensor Data Fusion: Trends, Solutions, Applications, SDF 2022, Bonn, Germany, October 12-14, 2022. pages 1-6, IEEE, 2022. [doi]

Abstract

Abstract is missing.