跳到主要导航 跳到搜索 跳到主要内容

Video Relation Detection with Trajectory-aware Multi-modal Features

  • Wentao Xie
  • , Guanghui Ren
  • , Si Liu*
  • *此作品的通讯作者
  • Beihang University
  • YITU Technology

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Video relation detection problem refers to the detection of the relationship between different objects in videos, such as spatial relationship and action relationship. In this paper, we present video relation detection with trajectory-aware multi-modal features to solve this task. Considering the complexity of doing visual relation detection in videos, we decompose this task into three sub-tasks: object detection, trajectory proposal and relation prediction. We use the state-of-the-art object detection method to ensure the accuracy of object trajectory detection and multi-modal feature representation to help the prediction of relation between objects. Our method won the first place on the video relation detection task of Video Relation Understanding Grand Challenge in ACM Multimedia 2020 with 11.74% mAP, which surpasses other methods by a large margin.

源语言英语
主期刊名MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
出版商Association for Computing Machinery, Inc
4590-4594
页数5
ISBN(电子版)9781450379885
DOI
出版状态已出版 - 12 10月 2020
活动28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, 美国
期限: 12 10月 202016 10月 2020

出版系列

姓名MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia

会议

会议28th ACM International Conference on Multimedia, MM 2020
国家/地区美国
Virtual, Online
时期12/10/2016/10/20

指纹

探究 'Video Relation Detection with Trajectory-aware Multi-modal Features' 的科研主题。它们共同构成独一无二的指纹。

引用此