SANet：Structure-Aware Network for Visual Tracking 阅读笔记
本文概览 解决问题：由于CNN模型主要用于类间判别，所以大多数CNN用于目标跟踪的任务中对目标物体的相似物都很敏感； 主要方法：CNN+RNN，CNN主要提供目标物体和背景之间的判别形，RNN主要提供目标物体和相似物之间的判别性； 主要思路：使用RNN对目标物体的self-structure信息建模，利用目标物体的self-structure信息加强目标物体与其相似物的判别性，并将目标物体的RNN
相关文章
- 1. DCFNet: Discriminant Correlation Filters Network for Visual Tracking 阅读
- 2. DSiam阅读笔记：Learning Dynamic Siamese Network for Visual Object Tracking
- 3. High Performance Visual Tracking with Siamese Region Proposal Network 阅读笔记
- 4. SiameseRPN: High Performance Visual Tracking with Siamese Region Proposal Network论文阅读笔记
- 5. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 阅读笔记
- 6. VITAL: Visual Tracking via Adversarial Learning 阅读笔记
- 7. SA-Siam阅读笔记：A Twofold Siamese Network for Real-Time Object Tracking
- 8. Learning Dynamic Siamese Network for Visual Object Tracking—ICCV2017 阅读
- 9. DASiamRPN阅读笔记：Distractor-aware Siamese Networks for Visual Object Tracking
- 10. 【Martin Danelljan PhD论文】Learning Convolution Operators for Visual Tracking 阅读笔记
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. DCFNet: Discriminant Correlation Filters Network for Visual Tracking 阅读
- 2. DSiam阅读笔记：Learning Dynamic Siamese Network for Visual Object Tracking
- 3. High Performance Visual Tracking with Siamese Region Proposal Network 阅读笔记
- 4. SiameseRPN: High Performance Visual Tracking with Siamese Region Proposal Network论文阅读笔记
- 5. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 阅读笔记
- 6. VITAL: Visual Tracking via Adversarial Learning 阅读笔记
- 7. SA-Siam阅读笔记：A Twofold Siamese Network for Real-Time Object Tracking
- 8. Learning Dynamic Siamese Network for Visual Object Tracking—ICCV2017 阅读
- 9. DASiamRPN阅读笔记：Distractor-aware Siamese Networks for Visual Object Tracking
- 10. 【Martin Danelljan PhD论文】Learning Convolution Operators for Visual Tracking 阅读笔记