Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. In this paper, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). Moreover, we conduct experimental adaption of existing methods to show the difficulty and potential directions for solving this valuable and applicable task. Our data and code are available at https://github.com/THU-KEG/goal.
@article{arxiv.2303.14655,
title = {GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation},
author = {Ji Qi and Jifan Yu and Teng Tu and Kunyu Gao and Yifan Xu and Xinyu Guan and Xiaozhi Wang and Yuxiao Dong and Bin Xu and Lei Hou and Juanzi Li and Jie Tang and Weidong Guo and Hui Liu and Yu Xu},
journal= {arXiv preprint arXiv:2303.14655},
year = {2023}
}