YoTube : searching action proposal via recurrent and static regression networks

• Main Authors: Zhu, Hongyuan, Vial, Romain, Lu, Shijian, Peng, Xi, Fu, Huazhu, Tian, Yonghong, Cao, Xianbin
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2019
• 主題: Object Detection; DRNTU::Engineering::Computer science and engineering; Image Sequence Analysis
• 在線閱讀: https://hdl.handle.net/10356/80911; http://hdl.handle.net/10220/48139
• 機構: Nanyang Technological University

In this paper, we propose YoTube-a novel deep learning framework for generating action proposals in untrimmed videos, where each action proposal corresponds to a spatial-temporal tube that potentially locates one human action. Most of the existing works generate proposals by clustering low-level fea...