Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, which aims to generate captions for different events in the untrimmed video. We propose five types of contexts as well as two categories of event captioning models, and evaluate their contributions for event captioning from both accuracy and diversity aspects. The proposed captioning models are plugged into our pipeline system for the dense video captioning challenge. The overall system achieves the state-of-the-art performance on the dense-captioning events in video task with 9.91 METEOR score on the challenge testing set.
@article{arxiv.1907.05092,
title = {Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos},
author = {Shizhe Chen and Yuqing Song and Yida Zhao and Qin Jin and Zhaoyang Zeng and Bei Liu and Jianlong Fu and Alexander Hauptmann},
journal= {arXiv preprint arXiv:1907.05092},
year = {2019}
}
Comments
Winner solution in CVPR 2019 Activitynet Dense Video Captioning challenge