EgoCap and EgoFormer: First-person image captioning with context fusion

Zhuangzhuang Dai, Vu Tran, Andrew Markham, Niki Trigoni, M. Arif Rahman, Lahiru N. S. Wijayasingha, John A. Stankovic, Chen Li

Abstract: Highlights•First quantitative study of image captioning in an egocentric perspective.•Introduction of transformer-based context fusion architecture.•EgoCap, a sizable first-person image caption dataset, is released.