SFGANS Self-supervised Future Generator for human ActioN Segmentation
This incremental improvement benefits applications like autonomous cars, robotics, and healthcare by enhancing existing models for action segmentation.
The paper tackles the problem of action segmentation in untrimmed videos by introducing a self-supervised method that refines feature representations within the standard pipeline, resulting in improved performance across different sub-tasks without additional hyperparameter tuning.
The ability to locate and classify action segments in long untrimmed video is of particular interest to many applications such as autonomous cars, robotics and healthcare applications. Today, the most popular pipeline for action segmentation is composed of encoding the frames into feature vectors, which are then processed by a temporal model for segmentation. In this paper we present a self-supervised method that comes in the middle of the standard pipeline and generated refined representations of the original feature vectors. Experiments show that this method improves the performance of existing models on different sub-tasks of action segmentation, even without additional hyper parameter tuning.