Work

Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion

Year: 2020

Type: conference-paper

Abstract: Head pose estimation and face alignment constitute a backbone preprocessing for many applications relying on face analysis. While both are closely related tasks, they are generally addressed separately, e.g. by deducing the head pose from the landmark locations. In this paper, we propose to entwine face alignment and head pose tasks inside an attentional cascade. This cascade uses a geometry transfer network for integrating heterogeneous annotations to enhance landmark localization accuracy. Furthermore, we propose a doubly-conditional fusion scheme to select relevant feature maps, and regions thereof, based on a current head pose and landmark localization estimate. We empirically show the benefit of entwining head pose and landmark localization objectives inside our architecture, and that the proposed AC-DC model enhances the state-of-the-art accuracy on multiple databases for both face alignment and head pose estimation tasks.

Source: International Conference on Automatic Face and Gesture Recognition

DOI: 10.1109/fg47880.2020.00038

Authors: Arnaud Dapogny, Kevin Bailly, Matthieu Cord

Institutions: Centre National de la Recherche Scientifique, Sorbonne Université, LIP6, Institut Systèmes Intelligents et de Robotique

Language: English

Topic: Face recognition and analysis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Face Interpretation with deep and ensemble Learning