.png){kind=icon}
.png){kind=icon}
Return
Siamese network for object tracking with multi-granularity appearance representations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108003.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A reliable tracker has the ability to adapt to change of objects over time, and is robust and accurate. We build such a tracker by extracting semantic features using robust Siamese networks and multi-granularity color features. It incorporates a semantic model that can capture high quality semantic features and an appearance model that can describe object at pixel, local and global levels effectively. Furthermore, we propose a novel selective traverse algorithm to allocate weights to semantic models and appearance models dynamically for better tracking performance. During tracking, our tracker updates appearance representations for objects based on the recent tracking results. The proposed tracker operates at speeds that exceed the real-time requirement, and outperforms nearly all other state-of-the-art trackers on OTB2013/2015 and VOT-2016/2017 benchmarks. (c) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Object tracking
Siamese network
Appearance adaption
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W