Fully-convolutional Siamese networks for object tracking

Conference item

The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.

Authors: Bertinetto, L; Valmadre, J; Henriques, JF; Vedaldi, A; Torr, PHS

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: Computer Vision – ECCV 2016: Workshops Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II
• Pages: 850-865
• Series: Lecture Notes in Computer Science
• Series number: 9914
• Place of publication: Cham, Switzerland
• Publication date: 2016-11-03
• Acceptance date: 2016-07-21
• Event title: 14th European Conference on Computer Vision (ECCV 2016)
• Event location: Amsterdam, The Netherlands
• Event start date: 2016-10-08
• Event end date: 2016-10-16
• DOI: 10.1007/978-3-319-48881-3_56
• EISSN: 1611-3349
• ISSN: 0302-9743
• EISBN: 9783319488813
• ISBN: 9783319488806
• Language: English
• Keywords: Siamese-network; deep-learning; similarity-learning; object-tracking