Knowledge Commons of Institute of Automation,CAS
Learning Feature Embeddings for Discriminant Model based Tracking | |
Linyu Zheng1,2; Ming Tang1,2; Yingying Chen1,2; Jinqiao Wang1,2; Hanqing Lu1,2 | |
2020-08 | |
会议名称 | European Conference on Computer Vision |
页码 | 759–775 |
会议日期 | 2020-8 |
会议地点 | Online |
摘要 | After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking. Our method, called DCFST, integrates the solver of a discriminant model that is differentiable and has a closed-form solution into convolutional neural networks. Then, the resulting network can be trained in an end-to-end way, obtaining optimal feature embeddings for the discriminant model-based tracker. As an instance, we apply the popular ridge regression model in this work to demonstrate the power of DCFST. Extensive experiments on six public benchmarks, OTB2015, NFS, GOT10k, TrackingNet, VOT2018, and VOT2019, show that our approach is efficient and generalizes well to class-agnostic target objects in online tracking, thus achieves state-of-the-art accuracy, while running beyond the real-time speed. Code will be made available. |
收录类别 | EI |
资助项目 | National Nature Science Foundation of China[61876086] ; National Natural Science Foundation of China[61702510] ; National Natural Science Foundation of China[61806200] ; National Natural Science Foundation of China[61772527] |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44855 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Linyu Zheng |
作者单位 | 1.NLPR 2.CASIA |
第一作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
通讯作者单位 | 模式识别国家重点实验室; 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Linyu Zheng,Ming Tang,Yingying Chen,et al. Learning Feature Embeddings for Discriminant Model based Tracking[C],2020:759–775. |
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 | ||
Learning Feature Emb(450KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论