CIOMP OpenIR
Foreground Information Guidance for Siamese Visual Tracking
D. Q. Li and Y. Yu
2020
发表期刊Ieee Access
ISSN2169-3536
卷号8页码:55905-55914
摘要Existing Siamese network based trackers are easily disturbed by large deformation, occlusion and distractor objects in the background. By comparing these trackers, we observe that the monotonous positive pairs usually have limited challenging factors (Occlusion, Deformation, etc.), which may make the learned features less robust. In addition, the foreground information of the substantial training data is utilized directly without deeper exploration. Thus, the trackers cannot effectively discriminate the foreground from the semantic backgrounds. In this paper, we focus on modifying the Siamese tracker by enriching the positive pairs and taking further advantage of the foreground information. During the offline training phase, a simple sampling strategy is adopted to enrich the challenging factors in positive pairs, which can effectively enhance the robustness of the tracker. At the same time, we highlight the foreground information by padding the background, and the information is utilized to generate a novel padding loss, which guides the tracker to pay less attention to the distractors in the background. Moreover, an improved feature information fusion is adopted to update the template, so that the tracker can adapt to the drastic appearance changes. Comprehensive experiments on the OTB and the VOT benchmarks demonstrate that our proposed tracker can achieve outstanding performance in both accuracy and robustness.
DOI10.1109/access.2020.2982261
URL查看原文
收录类别SCI
语种英语
引用统计
文献类型期刊论文
条目标识符http://ir.ciomp.ac.cn/handle/181722/64534
专题中国科学院长春光学精密机械与物理研究所
推荐引用方式
GB/T 7714
D. Q. Li and Y. Yu. Foreground Information Guidance for Siamese Visual Tracking[J]. Ieee Access,2020,8:55905-55914.
APA D. Q. Li and Y. Yu.(2020).Foreground Information Guidance for Siamese Visual Tracking.Ieee Access,8,55905-55914.
MLA D. Q. Li and Y. Yu."Foreground Information Guidance for Siamese Visual Tracking".Ieee Access 8(2020):55905-55914.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Li-2020-Foreground I(2292KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[D. Q. Li and Y. Yu]的文章
百度学术
百度学术中相似的文章
[D. Q. Li and Y. Yu]的文章
必应学术
必应学术中相似的文章
[D. Q. Li and Y. Yu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Li-2020-Foreground Information Guidance for Si.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。