End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding

Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu

科研成果: 书/报告/会议事项章节会议稿件同行评审

30 引用 (Scopus)

摘要

Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner. One major challenge of end-to-end one-shot video grounding is the existence of videos frames that are either irrelevant to the language query or the labeled frames. Another challenge relates to the limited supervision, which might result in ineffective representation learning. To address these challenges, we designed an end-to-end model via Information Tree for One-Shot video grounding (IT-OS). Its key module, the information tree, can eliminate the interference of irrelevant frames based on branch search and branch cropping techniques. In addition, several self-supervised tasks are proposed based on the information tree to improve the representation learning under insufficient labeling. Experiments on the benchmark dataset demonstrate the effectiveness of our model.

源语言英语
主期刊名ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
编辑Smaranda Muresan, Preslav Nakov, Aline Villavicencio
出版商Association for Computational Linguistics (ACL)
8707-8717
页数11
ISBN(电子版)9781955917216
出版状态已出版 - 2022
活动60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, 爱尔兰
期限: 22 5月 202227 5月 2022

出版系列

姓名Proceedings of the Annual Meeting of the Association for Computational Linguistics
1
ISSN(印刷版)0736-587X

会议

会议60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
国家/地区爱尔兰
Dublin
时期22/05/2227/05/22

指纹

探究 'End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding' 的科研主题。它们共同构成独一无二的指纹。

引用此