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:
-
-
(Preview, Accepted manuscript, 6.2MB, Terms of use)
-
- Publisher copy:
- 10.1109/CVPR42600.2020.00661
Authors
- 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
- Copyright holder:
- Institute of Electrical and Electronics Engineers
- Copyright date:
- 2020
- Rights statement:
- © 2020 IEEE.
- Notes:
- This conference paper was presented at the Conference on Computer Vision and Pattern Recognition 2020 (CVPR), 14-19 June, Virtual. This is the accepted manuscript version of the paper. The final version is available online from the Institute of Electrical and Electronics Engineers at: https://doi.org/10.1109/CVPR42600.2020.00661
If you are the owner of this record, you can report an update to it here: Report update to this record