Towards Omni-Supervised Face Alignment for Large Scale Unlabeled Videos
This addresses the problem of reducing annotation effort for face alignment in videos, though it appears incremental as it builds on existing supervised methods by incorporating unlabeled data.
The paper tackles face alignment in videos by proposing a spatial-temporal relational reasoning network (STRRN) that uses large-scale unlabeled videos and labeled data to generate training annotations, achieving performance superior to most fully supervised state-of-the-art methods.
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos. Unlike existing fully supervised methods which rely on numerous annotations by hand, our learner exploits large scale unlabeled videos plus available labeled data to generate auxiliary plausible training annotations. Motivated by the fact that neighbouring facial landmarks are usually correlated and coherent across consecutive frames, our approach automatically reasons about discriminative spatial-temporal relationships among landmarks for stable face tracking. Specifically, we carefully develop an interpretable and efficient network module, which disentangles facial geometry relationship for every static frame and simultaneously enforces the bi-directional cycle-consistency across adjacent frames, thus allowing the modeling of intrinsic spatial-temporal relations from raw face sequences. Extensive experimental results demonstrate that our approach surpasses the performance of most fully supervised state-of-the-arts.