TY - GEN
T1 - Adaptive aggregation of arbitrary online trackers with a regret bound
AU - Song, Heon
AU - Suehiro, Daiki
AU - Uchida, Seiichi
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number JP17H06100 and JP18K18001.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - We propose an online visual-object tracking method that is robust even in an adversarial environment, where various disturbances may occur on the target appearance, etc. The proposed method is based on a delayed-Hedge algorithm for aggregating multiple arbitrary online trackers with adaptive weights. The robustness in the tracking performance is guaranteed theoretically in term of "regret" by the property of the delayed-Hedge algorithm. Roughly speaking, the proposed method can achieve a similar tracking performance as the best one among all the trackers to be aggregated in an adversarial environment. The experimental study on various tracking tasks shows that the proposed method could achieve state-of-the-art performance by aggregating various online trackers.
AB - We propose an online visual-object tracking method that is robust even in an adversarial environment, where various disturbances may occur on the target appearance, etc. The proposed method is based on a delayed-Hedge algorithm for aggregating multiple arbitrary online trackers with adaptive weights. The robustness in the tracking performance is guaranteed theoretically in term of "regret" by the property of the delayed-Hedge algorithm. Roughly speaking, the proposed method can achieve a similar tracking performance as the best one among all the trackers to be aggregated in an adversarial environment. The experimental study on various tracking tasks shows that the proposed method could achieve state-of-the-art performance by aggregating various online trackers.
UR - http://www.scopus.com/inward/record.url?scp=85085491092&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085491092&partnerID=8YFLogxK
U2 - 10.1109/WACV45572.2020.9093613
DO - 10.1109/WACV45572.2020.9093613
M3 - Conference contribution
AN - SCOPUS:85085491092
T3 - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
SP - 670
EP - 678
BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Y2 - 1 March 2020 through 5 March 2020
ER -