ROAM : Recurrently Optimizing Tracking Model

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

121 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings 2020 IEEE/CVF International Conference on Computer Vision and Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages6717-6726
ISBN (electronic)9781728171685
ISBN (print)9781728171692
Publication statusPublished - Jun 2020

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
ISSN (Print)1063-6919
ISSN (electronic)2575-7075

Conference

Title2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
LocationVirtual
PlaceUnited States
CitySeattle
Period13 - 19 June 2020

Abstract

In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations. Thanks to the resizable convolutional filters used in both components to adapt to the shape changes of objects, our tracking model does not need to enumerate different sized anchors, thus saving model parameters. To effectively adapt the model to appearance variations, we propose to offline train a recurrent neural optimizer to update tracking model in a meta-learning setting, which can converge the model in a few gradient steps. This improves the convergence speed of updating the tracking model while achieving better performance. We extensively evaluate our trackers, ROAM and ROAM++, on the OTB, VOT, LaSOT, GOT-10K and TrackingNet benchmark and our methods perform favorably against state-of-the-art algorithms.

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

ROAM: Recurrently Optimizing Tracking Model. / Yang, Tianyu; Xu, Pengfei; Hu, Runbo et al.
Proceedings 2020 IEEE/CVF International Conference on Computer Vision and Pattern Recognition. Institute of Electrical and Electronics Engineers, Inc., 2020. p. 6717-6726 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review