A review on deep-learning based egocentric action anticipation

As autonomous systems become more embedded into our environments, the ability of these systems to anticipate the future actions of humans will become invaluable for providing assistance and safety measures. Egocentric action anticipation is a task in which a future activity must be predicted using first-person footage. This project is a survey that aims to provide an updated view of advancements within this task, to guide architecture design for future implementations. This survey has chosen a range of publicly available egocentric action anticipation models.