Charades-Ego Dataset

Charades-Ego Diagram

Charades-Ego is a dataset composed of 7,860 videos of daily indoors activities collected through Amazon Mechanical Turk recorded from both third and first person. The dataset contains 68,536 temporal annotations for 157 action classes.

Papers

Actor and Observer: Joint Modeling of First and Third-Person Videos

Gunnar Sigurdsson, Cordelia Schmid, Ali Farhadi, Abhinav Gupta, and Karteek Alahari CVPR  2018

Video