Conference item icon

Conference item

Siam R-CNN: visual tracking by re-detection

Alternative title:
Conference paper
Abstract:
We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking. We combine this with a novel tracklet-based dynamic programming algorithm, which takes advantage of re-detections of both the first-frame template and previous-frame predictions, to model the full history of both the object to be tracked and potential distractor objects. This enables our approach to make better tracking decisions, as well as to re-detect tracked objects after long occlusion. Finally, we propose a novel hard example mining strategy to improve Siam R-CNN's robustness to similar looking objects. Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. We make our code and models available at www.vision.rwth-aachen.de/page/siamrcnn.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR42600.2020.00661

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
Institute of Electrical and Electronics Engineers
Host title:
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Pages:
6577-6587
Publication date:
2020-08-05
Acceptance date:
2020-02-27
Event title:
Computer Vision and Pattern Recognition 2020
Event location:
Computer Vision and Pattern Recognition 2020
Event website:
Virtual
Event start date:
2020-06-14
Event end date:
2020-06-19
DOI:
EISSN:
1063-6919
ISSN:
2575-7075
EISBN:
9781728171685
ISBN:
9781728171692


Language:
English
Keywords:
Pubs id:
1114861
Local pid:
pubs:1114861
Deposit date:
2020-06-26

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP