Egocentric and Exocentric Methods: A Short Survey

TL;DR

This survey reviews recent advances in combining egocentric and exocentric vision methods, highlighting datasets, applications, and the potential for improved AI agents through multi-view modeling.

Contribution

It provides a comprehensive overview of the emerging field of joint egocentric and exocentric vision research, including datasets and key applications.

Findings

Identification of key datasets for egocentric-exocentric research

Summary of main applications in multi-view video understanding

Highlighting the potential of combined views for AI development

Abstract

Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The community has regained interest in the field of egocentric vision. While the third-person view and first-person have been thoroughly investigated, very few works aim to study both synchronously. Exocentric videos contain many relevant signals that are transferrable to egocentric videos. This paper provides a timely overview of works combining egocentric and exocentric visions, a very new but promising research topic. We describe in detail the datasets and present a survey of the key applications of ego-exo joint learning, where we identify the most recent advances. With the presentation of the current status of the progress, we believe this short but timely survey will be valuable to the broad video-understanding community, particularly when multi-view modeling is critical.