We aim to develop an AI agent that can watch video clips and have a conversation with human about the video story. Developing video understanding intelligence is a significantly challenging task, and evaluation methods for adequately measuring and analyzing the progress of AI agent are lacking as well. In this paper, we propose the Video Turing Test to provide effective and practical assessments of video understanding intelligence as well as human-likeness evaluation of AI agents. We define a general format and procedure of the Video Turing Test and present a case study to confirm the effectiveness and usefulness of the proposed test.
@article{arxiv.2110.04203,
title = {Toward a Human-Level Video Understanding Intelligence},
author = {Yu-Jung Heo and Minsu Lee and Seongho Choi and Woo Suk Choi and Minjung Shin and Minjoon Jung and Jeh-Kwang Ryu and Byoung-Tak Zhang},
journal= {arXiv preprint arXiv:2110.04203},
year = {2021}
}
Comments
Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836). The first two authors have equal contribution