In this paper we present VideoSET, a method for Video Summary Evaluation through Text that can evaluate how well a video summary is able to retain the semantic information contained in its original video. We observe that semantics is most easily expressed in words, and develop a text-based approach for the evaluation. Given a video summary, a text representation of the video summary is first generated, and an NLP-based metric is then used to measure its semantic distance to ground-truth text summaries written by humans. We show that our technique has higher agreement with human judgment than pixel-based distance metrics. We also release text annotations and ground-truth text summaries for a number of publicly available video datasets, for use by the computer vision community.
@article{arxiv.1406.5824,
title = {VideoSET: Video Summary Evaluation through Text},
author = {Serena Yeung and Alireza Fathi and Li Fei-Fei},
journal= {arXiv preprint arXiv:1406.5824},
year = {2014}
}