Temporal action detection based on hierarchical object detection networks

Yi Hui Wu, Wen Jiin Tsai, Hua Tsung Chen

研究成果: Conference contribution同行評審

摘要

This paper addresses the problem of temporal action detection from untrimmed videos. Considering that actions can be recognized by the occurrence of objects and the corresponding moving information in the video, a hierarchical model is proposed which consists of two object detection networks to do temporal action detection. The first network is used to detect objects in each frame, and the second one is for temporal action detection. We also proposed a method which converts the object detection results of the first network into a new type of frame so that it can be fed to the second network. The generated frame has six channels with spatiotemporal information beneficial to action detection. Quantitative results on THUMOS14 dataset demonstrate the superior of the proposed model with satisfactory performance gains over state-of-the-art action detection methods.

原文English
主出版物標題Proceedings - 2019 12th International Conference on Ubi-Media Computing, Ubi-Media 2019
發行者Institute of Electrical and Electronics Engineers Inc.
頁面119-123
頁數5
ISBN(電子)9781728128207
DOIs
出版狀態Published - 8月 2019
事件12th International Conference on Ubi-Media Computing, Ubi-Media 2019 - Bali, Indonesia
持續時間: 6 8月 20199 8月 2019

出版系列

名字Proceedings - 2019 12th International Conference on Ubi-Media Computing, Ubi-Media 2019

Conference

Conference12th International Conference on Ubi-Media Computing, Ubi-Media 2019
國家/地區Indonesia
城市Bali
期間6/08/199/08/19

指紋

深入研究「Temporal action detection based on hierarchical object detection networks」主題。共同形成了獨特的指紋。

引用此