Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Deep regression tracking with shrinkage loss
Author: Lu, X.
Ma, C.
Ni, B.
Yang, X.
Reid, I.
Yang, M.
Citation: Lecture Notes in Artificial Intelligence, 2018 / Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (ed./s), vol.11218 LNCS, pp.369-386
Publisher: Springer
Issue Date: 2018
Series/Report no.: Lecture Notes in Computer Science; 11218
ISBN: 9783030012632
ISSN: 0302-9743
Conference Name: European Conference on Computer Vision (ECCV) (8 Sep 2018 - 14 Sep 2018 : Munich)
Editor: Ferrari, V.
Hebert, M.
Sminchisescu, C.
Weiss, Y.
Statement of
Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, Ian Reid and Ming-Hsuan Yang
Abstract: Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions. Due to the potential for fast-tracking and easy implementation, regression trackers have recently received increasing attention. However, state-of-the-art deep regression trackers do not perform as well as discriminative correlation filters (DCFs) trackers. We identify the main bottleneck of training regression networks as extreme foreground-background data imbalance. To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data. Additionally, we apply residual connections to fuse multiple convolutional layers as well as their output response maps. Without bells and whistles, the proposed deep regression tracking method performs favorably against state-of-the-art trackers, especially in comparison with DCFs trackers, on five benchmark datasets including OTB-2013, OTB-2015, Temple-128, UAV-123 and VOT-2016.
Keywords: Regression networks; shrinking loss; object tracking
Rights: © Springer Nature Switzerland AG 2018
DOI: 10.1007/978-3-030-01264-9_22
Grant ID:
Published version:
Appears in Collections:Aurora harvest 8
Australian Institute for Machine Learning publications
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.