META-GRAPH ADAPTATION FOR VISUAL OBJECT TRACKING

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

5 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2021 IEEE International Conference on Multimedia and Expo (ICME)
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Number of pages6
ISBN (electronic)978-1-6654-1152-3
ISBN (print)978-1-6654-3864-3
Publication statusPublished - Jul 2021

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (electronic)1945-788X

Conference

Title2021 IEEE International Conference on Multimedia and Expo (ICME 2021)
LocationVirtual
PlaceChina
CityShenzhen
Period5 - 9 July 2021

Abstract

Existing deep trackers typically use offline-learned backbone networks for feature extraction across various online tracking tasks. However, for unseen objects, offline-learned representations are still limited due to the lack of adaptation. In this paper, we propose a Meta-Graph Adaptation Network (MGA-Net) to adapt backbones of deep trackers to specific online tracking tasks in a meta-learning fashion. Our MGA-Net is composed of a gradient embedding module (GEM) and a filter adaptation module (FAM). GEM takes gradients as an adaptation signal, and applies graph-message propagation to learn smoothed low-dimensional gradient embeddings. FAM utilizes both the learned gradient embeddings and the target exemplar to adapt the filter weights for the specific tracking task. MGA-Net can be end-to-end trained in an offline meta-learning way, and runs completely feed-forward for testing, thus enabling highly-efficient online tracking. We show that MGA-Net is generic and demonstrate its effectiveness in both template matching and correlation filter tracking frameworks.

Research Area(s)

  • Visual tracking, meta learning, Meta-graph adaptation, single object tracking, real-time tracking

Citation Format(s)

META-GRAPH ADAPTATION FOR VISUAL OBJECT TRACKING. / Wu, Qiangqiang; Chan, Antoni B.
2021 IEEE International Conference on Multimedia and Expo (ICME). Institute of Electrical and Electronics Engineers, Inc., 2021. (Proceedings - IEEE International Conference on Multimedia and Expo).

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