Multi-Branch Siamese Networks with Online Selection for Object Tracking [r-libre/1516]

Li, Zhenxi; Bilodeau, Guillaume-Alexandre, & Bouachir, Wassim (2018). Multi-Branch Siamese Networks with Online Selection for Object Tracking. In Bebis, Georges; Boyle, Richard; Parvin, Bahram; Koracin, Darko; Turek, Matt; Ramalingam, Srikumar; Xu, Kai; Lin, Stephen; Alsallakh, Bilal; Yang, Jing; Cuervo, Eduardo, & Ventura, Jonathan (Ed.), Advances in Visual Computing : 13th International Symposium, ISVC 2018, Las Vegas, NV, USA, November 19-21, 2018, Proceedings. Cham, Suisse : Springer, coll. « Lecture Notes in Computer Science », vol. 11241. https://doi.org/10.1007/978-3-030-03801-4_28

File(s) available for this item:

PDF - ISVC.pdf
Content : Accepted Version

Download

Item Type:	Papers in Conference Proceedings
Refereed:	Yes
Status:	Published
Abstract:	In this paper, we propose a robust object tracking algorithm based on a branch selection mechanism to choose the most efficient object representations from multi-branch siamese networks. While most deep learning trackers use a single CNN for target representation, the proposed Multi-Branch Siamese Tracker (MBST) employs multiple branches of CNNs pre-trained for different tasks, and used for various target representations in our tracking method. With our branch selection mechanism, the appropriate CNN branch is selected depending on the target characteristics in an online manner. By using the most adequate target representation with respect to the tracked object, our method achieves real-time tracking, while obtaining improved performance compared to standard Siamese network trackers on object tracking benchmarks.
Depositor:	Bouachir, Wassim
Owner / Manager:	Wassim Bouachir
Deposited:	03 Oct 2018 15:55
Last Modified:	20 Sep 2019 12:54

Actions (login required)

RÉVISER