Deformable Object Tracking With Gated Fusion

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

15 Scopus Citations
View graph of relations


  • Wenxi Liu
  • Dengsheng Chen
  • Shengfeng He
  • Yuanlong Yu
  • Tao Yan

Related Research Unit(s)


Original languageEnglish
Article number8662649
Pages (from-to)3766-3777
Journal / PublicationIEEE Transactions on Image Processing
Issue number8
Online published7 Mar 2019
Publication statusPublished - Aug 2019


The tracking-by-detection framework receives growing attention through the integration with the convolutional neural networks (CNNs). Existing tracking-by-detection-based methods, however, fail to track objects with severe appearance variations. This is because the traditional convolutional operation is performed on fixed grids, and thus may not be able to find the correct response while the object is changing pose or under varying environmental conditions. In this paper, we propose a deformable convolution layer to enrich the target appearance representations in the tracking-by-detection framework. We aim to capture the target appearance variations via deformable convolution, which adaptively enhances its original features. In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance. The enriched feature representation through deformable convolution facilitates the discrimination of the CNN classifier on the target object and background. The extensive experiments on the standard benchmarks show that the proposed tracker performs favorably against the state-of-the-art methods.

Research Area(s)

  • deformable convolution, gating, Visual tracking

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Deformable Object Tracking With Gated Fusion. / Liu, Wenxi; Song, Yibing; Chen, Dengsheng; He, Shengfeng; Yu, Yuanlong; Yan, Tao; Hancke, Gehard P.; Lau, Rynson W. H.

In: IEEE Transactions on Image Processing, Vol. 28, No. 8, 8662649, 08.2019, p. 3766-3777.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review