Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for video understanding. While several previous studies have suggested datasets for video Q&A tasks, they did not really incorporate story-level understanding, resulting in highly-biased and lack of variance in degree of question difficulty. In this paper, we propose a hierarchical method for building Q&A datasets, i.e. hierarchical difficulty levels. We introduce three criteria for video story understanding, i.e. memory capacity, logical complexity, and DIKW (Data-Information-Knowledge-Wisdom) pyramid. We discuss how three-dimensional map constructed from these criteria can be used as a metric for evaluating the levels of intelligence relating to video story understanding.
@article{arxiv.1904.00623,
title = {Constructing Hierarchical Q&A Datasets for Video Story Understanding},
author = {Yu-Jung Heo and Kyoung-Woon On and Seongho Choi and Jaeseo Lim and Jinah Kim and Jeh-Kwang Ryu and Byung-Chull Bae and Byoung-Tak Zhang},
journal= {arXiv preprint arXiv:1904.00623},
year = {2019}
}
Comments
Accepted to AAAI 2019 Spring Symposium Series : Story-Enabled Intelligence