META-GRAPH ADAPTATION FOR VISUAL OBJECT TRACKING
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | 2021 IEEE International Conference on Multimedia and Expo (ICME) |
Publisher | Institute of Electrical and Electronics Engineers, Inc. |
Number of pages | 6 |
ISBN (electronic) | 978-1-6654-1152-3 |
ISBN (print) | 978-1-6654-3864-3 |
Publication status | Published - Jul 2021 |
Publication series
Name | Proceedings - IEEE International Conference on Multimedia and Expo |
---|---|
ISSN (Print) | 1945-7871 |
ISSN (electronic) | 1945-788X |
Conference
Title | 2021 IEEE International Conference on Multimedia and Expo (ICME 2021) |
---|---|
Location | Virtual |
Place | China |
City | Shenzhen |
Period | 5 - 9 July 2021 |
Link(s)
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).
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 Works › RGC 32 - Refereed conference paper (with host publication) › peer-review