.png){kind=icon}
返回
Capturing Relevant Context for Visual Tracking
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2020.3038310.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Studies have shown that contextual information can promote the robustness of trackers. However, trackers based on convolutional neural networks (CNNs) only capture local features, which limits their performance. We propose a novel relevant context block (RCB), which employs graph convolutional networks to capture the relevant context. In particular, it selects the k largest contributors as nodes for each query position (unit) that contain meaningful and discriminative contextual information and updates the nodes by aggregating the differences between the query position and its contributors. This operation can be easily incorporated into the existing networks and can be easily end-to-end trained using a standard backpropagation algorithm. To verify the effectiveness of RCB, we apply it to two trackers, SiamFC and GlobalTrack, respectively, and the two improved trackers are referred to as Siam-RCB andGlobalTrack-RCB. Extensive experiments onOTB, VOT, UAV123, LaSOT, TrackingNet, OxUvA, and VOT2018LT show the superiority of our method. For example, our Siam-RCB outperforms SiamFC by a very large margin (up to 11.2% in the success score and 7.8% in the precision score) on the OTB-100 benchmark.
Keyword:
Local neighborhood graph
long-range dependencies
long-term tracking
visual object tracking
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
NK cell CD16 surface expression and function is regulated by a disintegrin and metalloprotease-17 (ADAM17).png)
Blood
OAAI
BloodIF0
OAAI分享收藏
查看更多内容