Context-aware Deep Feature Compression for High-speed Visual Tracking

File Description SizeFormat 
cvpr2018-traca-paper-stamped.pdfFile embargoed until 01 January 100001.99 MBAdobe PDF    Request a copy
Title: Context-aware Deep Feature Compression for High-speed Visual Tracking
Author(s): Choi, J
Chang, HJ
Fischer, T
Yun, S
Lee, K
Jeong, J
Demiris, Y
Choi, JY
Item Type: Conference Paper
Abstract: We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.
Publication Date: 6-Jun-2018
Date of Acceptance: 28-Feb-2018
ISSN: 1063-6919
Publisher: Institute of Electrical and Electronics Engineers
Journal / Book Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition
Copyright Statement: This paper is embargoed until publication.
Keywords: cs.CV
Publication Status: Accepted
Start Date: 2018-06-18
Finish Date: 2018-06-22
Conference Place: Salt Lake City, Utah, USA
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering

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

Creative Commons