TY - GEN
T1 - Real-time Spatio-Temporal Action Localization in 360 Videos
AU - Chen, Bo
AU - Ali-Eldin, Ahmed
AU - Shenoy, Prashant
AU - Nahrstedt, Klara
N1 - Funding Information:
ACKNOWLEDGEMENT This work was partially supported by the US Army Research Laboratory under cooperative agreement W911NF17- 2-0196. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the US government.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - Spatio-temporal action localization of human actions in a video has been a popular topic over the past few years. It tries to localize the bounding boxes, the time span and the class of one action, which summarizes information in the video and helps humans understand it. Though many approaches have been proposed to solve this problem, these efforts have only focused on perspective videos. Unfortunately, perspective videos only cover a small field-of-view (FOV), which limits the capability of action localization. In this paper, we develop a comprehensive approach to real-time spatio-temporallocalization that can be used to detect actions in 360 videos. We create two datasets named UCF-101-24-360 and JHMDB-21-360 for our evaluation. Our experiments show that our method consistently outperforms other competing approaches and achieves a real-time processing speed of 15fps for 360 videos.
AB - Spatio-temporal action localization of human actions in a video has been a popular topic over the past few years. It tries to localize the bounding boxes, the time span and the class of one action, which summarizes information in the video and helps humans understand it. Though many approaches have been proposed to solve this problem, these efforts have only focused on perspective videos. Unfortunately, perspective videos only cover a small field-of-view (FOV), which limits the capability of action localization. In this paper, we develop a comprehensive approach to real-time spatio-temporallocalization that can be used to detect actions in 360 videos. We create two datasets named UCF-101-24-360 and JHMDB-21-360 for our evaluation. Our experiments show that our method consistently outperforms other competing approaches and achieves a real-time processing speed of 15fps for 360 videos.
KW - 360 video
KW - Spatio temporal action localization
UR - http://www.scopus.com/inward/record.url?scp=85101451828&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101451828&partnerID=8YFLogxK
U2 - 10.1109/ISM.2020.00018
DO - 10.1109/ISM.2020.00018
M3 - Conference contribution
AN - SCOPUS:85101451828
T3 - Proceedings - 2020 IEEE International Symposium on Multimedia, ISM 2020
SP - 73
EP - 76
BT - Proceedings - 2020 IEEE International Symposium on Multimedia, ISM 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Symposium on Multimedia, ISM 2020
Y2 - 2 December 2020 through 4 December 2020
ER -