GLAIVE: Graphics-based Learning Approach Integrated with Vision Elements

GLAIVE: Graphics-based Learning Approach Integrated with Vision Elements

The GLAIVE project is part of IARPA Janus program which focuses on improving the current performance of face recognition tools by fusing the rich spatial, temporal, and contextual information available from the multiple views captured by today’s “media in the wild”.  As part of the GLAIVE project, our goal is to build new technologies for automatic facial landmark detection. This project builds upon our existing expertise with neural networks and conditional discriminative models including the Constrained Local Neural Field model.